Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2405 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4201. Min Range: -6.4201
Max Act: 6.4201. Min Act: -0.1700
Data Index: 8566094 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4201. Min Range: -6.4201
Max Act: 6.0763. Min Act: -0.1700
Data Index: 2898977 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4201. Min Range: -6.4201
Max Act: 6.0138. Min Act: -0.1700
Data Index: 8269348 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4201. Min Range: -6.4201
Max Act: 6.0138. Min Act: -0.1700
Data Index: 6721842 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.9826. Min Act: -0.1700
Data Index: 7105492 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.9826. Min Act: -0.1700
Data Index: 3940941 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.9513. Min Act: -0.1700
Data Index: 6872566 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.9513. Min Act: -0.1700
Data Index: 939051 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.9826. Min Act: -0.1700
Data Index: 1768965 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.9826. Min Act: -0.1700
Data Index: 1635834 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.9513. Min Act: -0.1700
Data Index: 5058980 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.9201. Min Act: -0.1700
Data Index: 7413557 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.9201. Min Act: -0.1700
Data Index: 3098668 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.9201. Min Act: -0.1700
Data Index: 8755484 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.9201. Min Act: -0.1700
Data Index: 3898572 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.9201. Min Act: -0.1700
Data Index: 7320342 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.8888. Min Act: -0.1700
Data Index: 2506747 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.8888. Min Act: -0.1700
Data Index: 6484446 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.8888. Min Act: -0.1700
Data Index: 2580972 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4201. Min Range: -6.4201
Max Act: 5.8888. Min Act: -0.1700
Data Index: 7859210 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19