Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5022 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2981. Min Range: -7.2981
Max Act: 7.2981. Min Act: -0.1700
Data Index: 3411172 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2981. Min Range: -7.2981
Max Act: 7.0168. Min Act: -0.1700
Data Index: 7407004 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.7981. Min Act: -0.1700
Data Index: 7297613 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.6731. Min Act: -0.1700
Data Index: 6942790 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.6106. Min Act: -0.1700
Data Index: 5791224 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.6106. Min Act: -0.1700
Data Index: 8439290 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.5793. Min Act: -0.1700
Data Index: 5128176 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.5168. Min Act: -0.1700
Data Index: 4570829 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.5168. Min Act: -0.1700
Data Index: 7727774 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.4856. Min Act: -0.1700
Data Index: 1670737 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.4856. Min Act: -0.1700
Data Index: 1132765 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.4543. Min Act: -0.1700
Data Index: 1026237 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.4231. Min Act: -0.1700
Data Index: 7032497 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.4231. Min Act: -0.1700
Data Index: 21429 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.4231. Min Act: -0.1700
Data Index: 493119 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.3918. Min Act: -0.1700
Data Index: 59065 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.3606. Min Act: -0.1700
Data Index: 6028249 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.3918. Min Act: -0.1700
Data Index: 4885939 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.3918. Min Act: -0.1700
Data Index: 4286445 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2981. Min Range: -7.2981
Max Act: 6.4231. Min Act: -0.1700
Data Index: 6291252 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19