Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3228. Min Range: -7.3228
Max Act: 7.3228. Min Act: -0.1700
Data Index: 6264533 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3228. Min Range: -7.3228
Max Act: 7.2290. Min Act: -0.1700
Data Index: 3375624 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3228. Min Range: -7.3228
Max Act: 7.0415. Min Act: -0.1700
Data Index: 6119435 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.8853. Min Act: -0.1700
Data Index: 1200375 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.8228. Min Act: -0.1700
Data Index: 7786018 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.7603. Min Act: -0.1700
Data Index: 1732674 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.7603. Min Act: -0.1700
Data Index: 5717655 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.7603. Min Act: -0.1700
Data Index: 6644380 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.6353. Min Act: -0.1700
Data Index: 1505876 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.6353. Min Act: -0.1700
Data Index: 5617494 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.5728. Min Act: -0.1700
Data Index: 6475075 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.5728. Min Act: -0.1700
Data Index: 3601785 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.5728. Min Act: -0.1700
Data Index: 7621777 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.5415. Min Act: -0.1700
Data Index: 6485852 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.5415. Min Act: -0.1700
Data Index: 3524235 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.5415. Min Act: -0.1700
Data Index: 6173593 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.5103. Min Act: -0.1700
Data Index: 3651716 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.4790. Min Act: -0.1700
Data Index: 6069603 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.4790. Min Act: -0.1700
Data Index: 3452650 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3228. Min Range: -7.3228
Max Act: 6.4790. Min Act: -0.1700
Data Index: 5705521 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19