Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5192 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2714. Min Range: -7.2714
Max Act: 7.2714. Min Act: -0.1700
Data Index: 7117005 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.9589. Min Act: -0.1700
Data Index: 2172493 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.9277. Min Act: -0.1700
Data Index: 4898718 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.6152. Min Act: -0.1700
Data Index: 4092237 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.5839. Min Act: -0.1700
Data Index: 6293888 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.5214. Min Act: -0.1700
Data Index: 219421 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.5527. Min Act: -0.1700
Data Index: 3719954 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.5214. Min Act: -0.1700
Data Index: 7220318 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.4902. Min Act: -0.1700
Data Index: 3537152 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.4589. Min Act: -0.1700
Data Index: 5609542 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.4589. Min Act: -0.1700
Data Index: 4478550 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.4277. Min Act: -0.1700
Data Index: 7842119 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.4277. Min Act: -0.1700
Data Index: 1802698 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.3964. Min Act: -0.1700
Data Index: 5089897 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.3964. Min Act: -0.1700
Data Index: 6339284 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.3964. Min Act: -0.1700
Data Index: 5973096 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.3652. Min Act: -0.1700
Data Index: 6944231 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.3652. Min Act: -0.1700
Data Index: 2409725 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.3652. Min Act: -0.1700
Data Index: 5688533 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2714. Min Range: -7.2714
Max Act: 6.3652. Min Act: -0.1700
Data Index: 2290347 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19