Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 917 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.8228. Min Act: -0.1700
Data Index: 4328693 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.6666. Min Act: -0.1700
Data Index: 7508315 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.5728. Min Act: -0.1700
Data Index: 8055809 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.5728. Min Act: -0.1700
Data Index: 7815241 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.4166. Min Act: -0.1700
Data Index: 666724 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.3228. Min Act: -0.1700
Data Index: 7799116 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.3541. Min Act: -0.1700
Data Index: 6095744 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.3228. Min Act: -0.1700
Data Index: 3246665 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.3228. Min Act: -0.1700
Data Index: 3134038 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.3228. Min Act: -0.1700
Data Index: 2349626 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.2603. Min Act: -0.1700
Data Index: 5671591 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.2916. Min Act: -0.1700
Data Index: 8057539 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.2603. Min Act: -0.1700
Data Index: 114556 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.2603. Min Act: -0.1700
Data Index: 8621873 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.2603. Min Act: -0.1700
Data Index: 6470297 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.2603. Min Act: -0.1700
Data Index: 1834815 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.2603. Min Act: -0.1700
Data Index: 6346023 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.2291. Min Act: -0.1700
Data Index: 5427955 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.2291. Min Act: -0.1700
Data Index: 6180927 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8228. Min Range: -6.8228
Max Act: 6.2291. Min Act: -0.1700
Data Index: 6603630 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19