Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 455 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1272. Min Range: -5.1272
Max Act: 5.1272. Min Act: -0.1700
Data Index: 5673864 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.8460. Min Act: -0.1700
Data Index: 3999609 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.7210. Min Act: -0.1700
Data Index: 5159992 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.6897. Min Act: -0.1700
Data Index: 1313266 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.6585. Min Act: -0.1700
Data Index: 5374699 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.6272. Min Act: -0.1700
Data Index: 2268941 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.5960. Min Act: -0.1700
Data Index: 4994302 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.5960. Min Act: -0.1700
Data Index: 747280 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.5960. Min Act: -0.1700
Data Index: 7542877 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.5335. Min Act: -0.1700
Data Index: 101251 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.5022. Min Act: -0.1700
Data Index: 4284911 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.5022. Min Act: -0.1700
Data Index: 8714517 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.5022. Min Act: -0.1700
Data Index: 5905558 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.5022. Min Act: -0.1700
Data Index: 5133841 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.4710. Min Act: -0.1700
Data Index: 7541622 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.4710. Min Act: -0.1700
Data Index: 763549 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.4710. Min Act: -0.1700
Data Index: 3133112 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.4710. Min Act: -0.1700
Data Index: 410701 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.4397. Min Act: -0.1700
Data Index: 6728869 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1272. Min Range: -5.1272
Max Act: 4.4397. Min Act: -0.1700
Data Index: 1690590 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19