Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1608 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.7587. Min Act: -0.1700
Data Index: 8033069 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.6649. Min Act: -0.1700
Data Index: 7891847 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.4462. Min Act: -0.1700
Data Index: 2121008 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.3524. Min Act: -0.1700
Data Index: 5665246 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.3524. Min Act: -0.1700
Data Index: 4054417 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.3524. Min Act: -0.1700
Data Index: 3721415 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.3212. Min Act: -0.1700
Data Index: 3241668 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.3212. Min Act: -0.1700
Data Index: 2891102 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.2899. Min Act: -0.1700
Data Index: 5112536 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.2899. Min Act: -0.1700
Data Index: 3373146 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.3212. Min Act: -0.1700
Data Index: 1857470 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.2587. Min Act: -0.1700
Data Index: 6362437 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.2274. Min Act: -0.1700
Data Index: 2750728 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.2274. Min Act: -0.1700
Data Index: 5735301 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.1962. Min Act: -0.1700
Data Index: 5497488 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.1962. Min Act: -0.1700
Data Index: 5596900 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.1649. Min Act: -0.1700
Data Index: 3139484 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.1962. Min Act: -0.1700
Data Index: 1579905 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.1962. Min Act: -0.1700
Data Index: 7789588 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7587. Min Range: -5.7587
Max Act: 5.1649. Min Act: -0.1700
Data Index: 6566670 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19