Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2518 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.9711. Min Act: -0.1700
Data Index: 7192170 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.9711. Min Act: -0.1700
Data Index: 5334386 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.9086. Min Act: -0.1700
Data Index: 1357156 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.7211. Min Act: -0.1700
Data Index: 268134 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.6586. Min Act: -0.1700
Data Index: 1826707 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.6586. Min Act: -0.1700
Data Index: 5168758 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.6586. Min Act: -0.1700
Data Index: 7354178 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.5961. Min Act: -0.1700
Data Index: 1956802 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.5336. Min Act: -0.1700
Data Index: 1514479 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.5336. Min Act: -0.1700
Data Index: 4344998 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.5336. Min Act: -0.1700
Data Index: 8785863 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.4086. Min Act: -0.1700
Data Index: 612645 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.4086. Min Act: -0.1700
Data Index: 1475882 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.3461. Min Act: -0.1700
Data Index: 1498067 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.3461. Min Act: -0.1700
Data Index: 8797775 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.2836. Min Act: -0.1700
Data Index: 947627 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.2836. Min Act: -0.1700
Data Index: 7189911 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.2836. Min Act: -0.1700
Data Index: 132358 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.2836. Min Act: -0.1700
Data Index: 4289468 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9711. Min Range: -10.9711
Max Act: 10.2836. Min Act: -0.1700
Data Index: 3460079 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19