Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2637 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.6295. Min Act: -0.1700
Data Index: 1799393 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.5670. Min Act: -0.1700
Data Index: 6297623 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.4733. Min Act: -0.1700
Data Index: 8533817 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.4733. Min Act: -0.1700
Data Index: 6706161 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.4420. Min Act: -0.1700
Data Index: 4897686 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.3795. Min Act: -0.1700
Data Index: 5150217 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.3795. Min Act: -0.1700
Data Index: 6752134 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.3170. Min Act: -0.1700
Data Index: 8497624 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.3483. Min Act: -0.1700
Data Index: 419698 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.3483. Min Act: -0.1700
Data Index: 5536597 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.3483. Min Act: -0.1700
Data Index: 5719861 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.3483. Min Act: -0.1700
Data Index: 3359864 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.2858. Min Act: -0.1700
Data Index: 2073707 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.2858. Min Act: -0.1700
Data Index: 7786228 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.2545. Min Act: -0.1700
Data Index: 7746131 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.2858. Min Act: -0.1700
Data Index: 2813482 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.2545. Min Act: -0.1700
Data Index: 4142690 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.2233. Min Act: -0.1700
Data Index: 6207957 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.2545. Min Act: -0.1700
Data Index: 1925951 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6295. Min Range: -4.6295
Max Act: 4.2233. Min Act: -0.1700
Data Index: 8118640 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19