Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2600 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.9166. Min Act: -0.1700
Data Index: 7859288 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.7603. Min Act: -0.1700
Data Index: 3071390 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.4166. Min Act: -0.1700
Data Index: 4797382 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.3541. Min Act: -0.1700
Data Index: 4943249 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.3541. Min Act: -0.1700
Data Index: 8366809 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.3541. Min Act: -0.1700
Data Index: 3867941 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.3228. Min Act: -0.1700
Data Index: 5616857 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.2916. Min Act: -0.1700
Data Index: 6400499 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.3228. Min Act: -0.1700
Data Index: 6876165 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.2603. Min Act: -0.1700
Data Index: 109010 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.2291. Min Act: -0.1700
Data Index: 6394601 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.2603. Min Act: -0.1700
Data Index: 3044846 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.2603. Min Act: -0.1700
Data Index: 1487174 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.2291. Min Act: -0.1700
Data Index: 2391046 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.2291. Min Act: -0.1700
Data Index: 4756352 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.1978. Min Act: -0.1700
Data Index: 5023326 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.2291. Min Act: -0.1700
Data Index: 2244148 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.1978. Min Act: -0.1700
Data Index: 7717965 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.1978. Min Act: -0.1700
Data Index: 7302379 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9166. Min Range: -6.9166
Max Act: 6.1666. Min Act: -0.1700
Data Index: 2654508 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19