Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.8742. Min Act: -0.1700
Data Index: 2954268 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.7805. Min Act: -0.1700
Data Index: 6782853 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.7805. Min Act: -0.1700
Data Index: 6820522 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.7180. Min Act: -0.1700
Data Index: 3131041 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.7180. Min Act: -0.1700
Data Index: 6408153 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.7180. Min Act: -0.1700
Data Index: 8558873 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.7180. Min Act: -0.1700
Data Index: 4103696 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.7180. Min Act: -0.1700
Data Index: 3899201 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.6867. Min Act: -0.1700
Data Index: 158881 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.6555. Min Act: -0.1700
Data Index: 873499 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.5930. Min Act: -0.1700
Data Index: 6859959 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.6242. Min Act: -0.1700
Data Index: 1145173 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.6242. Min Act: -0.1700
Data Index: 6314324 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.5617. Min Act: -0.1700
Data Index: 6640949 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.5617. Min Act: -0.1700
Data Index: 1588639 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.5617. Min Act: -0.1700
Data Index: 4501644 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.5617. Min Act: -0.1700
Data Index: 3213144 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.5305. Min Act: -0.1700
Data Index: 1787708 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.5305. Min Act: -0.1700
Data Index: 4301945 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8742. Min Range: -5.8742
Max Act: 5.5305. Min Act: -0.1700
Data Index: 873500 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19