Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1532 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2574. Min Range: -8.2574
Max Act: 8.2574. Min Act: -0.1700
Data Index: 5147158 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.8199. Min Act: -0.1700
Data Index: 5261339 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.7574. Min Act: -0.1700
Data Index: 1756929 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.6324. Min Act: -0.1700
Data Index: 3261477 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.6324. Min Act: -0.1700
Data Index: 7110168 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.5699. Min Act: -0.1700
Data Index: 776979 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.4761. Min Act: -0.1700
Data Index: 8504313 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.4761. Min Act: -0.1700
Data Index: 1691585 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.4136. Min Act: -0.1700
Data Index: 8164900 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.4449. Min Act: -0.1700
Data Index: 4660155 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.4761. Min Act: -0.1700
Data Index: 7245444 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.4136. Min Act: -0.1700
Data Index: 7068668 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.4136. Min Act: -0.1700
Data Index: 5159937 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.3511. Min Act: -0.1700
Data Index: 989483 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.3199. Min Act: -0.1700
Data Index: 3133849 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.3199. Min Act: -0.1700
Data Index: 5372204 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.2886. Min Act: -0.1700
Data Index: 5330987 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.2886. Min Act: -0.1700
Data Index: 3768337 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.2574. Min Act: -0.1700
Data Index: 3097854 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2574. Min Range: -8.2574
Max Act: 7.2574. Min Act: -0.1700
Data Index: 2697370 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19