Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3084 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.8818. Min Act: -0.1700
Data Index: 1972799 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7880. Min Act: -0.1700
Data Index: 6359393 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7880. Min Act: -0.1700
Data Index: 2846772 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7880. Min Act: -0.1700
Data Index: 6447303 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7880. Min Act: -0.1700
Data Index: 1458992 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7880. Min Act: -0.1700
Data Index: 5366551 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7880. Min Act: -0.1700
Data Index: 5850603 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7880. Min Act: -0.1700
Data Index: 4543165 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7880. Min Act: -0.1700
Data Index: 7140844 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7880. Min Act: -0.1700
Data Index: 1756617 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7880. Min Act: -0.1700
Data Index: 5468803 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7568. Min Act: -0.1700
Data Index: 1770079 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7255. Min Act: -0.1700
Data Index: 5295552 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7568. Min Act: -0.1700
Data Index: 5425028 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7255. Min Act: -0.1700
Data Index: 1030217 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7255. Min Act: -0.1700
Data Index: 5067177 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7255. Min Act: -0.1700
Data Index: 7208701 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7255. Min Act: -0.1700
Data Index: 8703786 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.7255. Min Act: -0.1700
Data Index: 2112594 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8818. Min Range: -5.8818
Max Act: 5.6943. Min Act: -0.1700
Data Index: 341774 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19