Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2198 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1586. Min Range: -10.1586
Max Act: 10.1586. Min Act: -0.1700
Data Index: 8224654 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1586. Min Range: -10.1586
Max Act: 9.3461. Min Act: -0.1700
Data Index: 7174134 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1586. Min Range: -10.1586
Max Act: 9.2836. Min Act: -0.1700
Data Index: 8319740 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1586. Min Range: -10.1586
Max Act: 9.2211. Min Act: -0.1700
Data Index: 1748648 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1586. Min Range: -10.1586
Max Act: 9.0961. Min Act: -0.1700
Data Index: 732728 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1586. Min Range: -10.1586
Max Act: 9.1586. Min Act: -0.1700
Data Index: 2893979 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1586. Min Range: -10.1586
Max Act: 9.0961. Min Act: -0.1700
Data Index: 103127 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1586. Min Range: -10.1586
Max Act: 9.0961. Min Act: -0.1700
Data Index: 7594533 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1586. Min Range: -10.1586
Max Act: 9.0336. Min Act: -0.1700
Data Index: 4561866 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1586. Min Range: -10.1586
Max Act: 9.0336. Min Act: -0.1700
Data Index: 4195893 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1586. Min Range: -10.1586
Max Act: 9.0336. Min Act: -0.1700
Data Index: 79328 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1586. Min Range: -10.1586
Max Act: 8.9711. Min Act: -0.1700
Data Index: 7426435 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1586. Min Range: -10.1586
Max Act: 8.9711. Min Act: -0.1700
Data Index: 8692068 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1586. Min Range: -10.1586
Max Act: 8.9086. Min Act: -0.1700
Data Index: 4945557 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1586. Min Range: -10.1586
Max Act: 8.9086. Min Act: -0.1700
Data Index: 987070 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1586. Min Range: -10.1586
Max Act: 8.8461. Min Act: -0.1700
Data Index: 5301648 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1586. Min Range: -10.1586
Max Act: 8.8461. Min Act: -0.1700
Data Index: 6833931 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1586. Min Range: -10.1586
Max Act: 8.8461. Min Act: -0.1700
Data Index: 5569071 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1586. Min Range: -10.1586
Max Act: 8.7836. Min Act: -0.1700
Data Index: 51209 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1586. Min Range: -10.1586
Max Act: 8.7836. Min Act: -0.1700
Data Index: 8242617 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19