Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5298 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.4083. Min Act: -0.1700
Data Index: 4330654 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.3771. Min Act: -0.1700
Data Index: 2754419 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.2833. Min Act: -0.1700
Data Index: 4225932 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.2208. Min Act: -0.1700
Data Index: 5656716 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.1583. Min Act: -0.1700
Data Index: 1870113 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.0646. Min Act: -0.1700
Data Index: 270946 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.0958. Min Act: -0.1700
Data Index: 6992389 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4083. Min Range: -7.4083
Max Act: 7.0333. Min Act: -0.1700
Data Index: 5032566 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.9083. Min Act: -0.1700
Data Index: 4075783 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.8771. Min Act: -0.1700
Data Index: 2923537 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.8771. Min Act: -0.1700
Data Index: 8741960 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.7833. Min Act: -0.1700
Data Index: 2872335 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.7833. Min Act: -0.1700
Data Index: 78097 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.7833. Min Act: -0.1700
Data Index: 1870118 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.7833. Min Act: -0.1700
Data Index: 5036899 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.7833. Min Act: -0.1700
Data Index: 4054106 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.7208. Min Act: -0.1700
Data Index: 1247703 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.7208. Min Act: -0.1700
Data Index: 6805400 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.6583. Min Act: -0.1700
Data Index: 953703 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4083. Min Range: -7.4083
Max Act: 6.6583. Min Act: -0.1700
Data Index: 7167382 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19