Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2855 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5223. Min Range: -7.5223
Max Act: 7.5223. Min Act: -0.1700
Data Index: 5713509 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.9911. Min Act: -0.1700
Data Index: 2001318 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.8036. Min Act: -0.1700
Data Index: 4540970 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.6161. Min Act: -0.1700
Data Index: 5642598 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.6161. Min Act: -0.1700
Data Index: 568113 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.5848. Min Act: -0.1700
Data Index: 3895263 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.5848. Min Act: -0.1700
Data Index: 1790260 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.5223. Min Act: -0.1700
Data Index: 561712 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.5223. Min Act: -0.1700
Data Index: 283312 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.4911. Min Act: -0.1700
Data Index: 4575390 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.4286. Min Act: -0.1700
Data Index: 3105265 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.4286. Min Act: -0.1700
Data Index: 3388470 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.3973. Min Act: -0.1700
Data Index: 5865617 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.3973. Min Act: -0.1700
Data Index: 6317975 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.3661. Min Act: -0.1700
Data Index: 6338540 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.3661. Min Act: -0.1700
Data Index: 8248268 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.3348. Min Act: -0.1700
Data Index: 320122 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.3348. Min Act: -0.1700
Data Index: 7436440 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.3348. Min Act: -0.1700
Data Index: 7429935 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5223. Min Range: -7.5223
Max Act: 6.3348. Min Act: -0.1700
Data Index: 3975108 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19