Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 233 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0472. Min Range: -6.0472
Max Act: 6.0472. Min Act: -0.1700
Data Index: 854200 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.9222. Min Act: -0.1700
Data Index: 3491706 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.8597. Min Act: -0.1700
Data Index: 3534441 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.8597. Min Act: -0.1700
Data Index: 928332 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.7972. Min Act: -0.1700
Data Index: 5379194 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.7972. Min Act: -0.1700
Data Index: 6696055 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.7972. Min Act: -0.1700
Data Index: 2476113 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.7347. Min Act: -0.1700
Data Index: 2484266 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.7347. Min Act: -0.1700
Data Index: 329628 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.7034. Min Act: -0.1700
Data Index: 6670900 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.7034. Min Act: -0.1700
Data Index: 7710368 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.7034. Min Act: -0.1700
Data Index: 6308911 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.6409. Min Act: -0.1700
Data Index: 4203267 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.6097. Min Act: -0.1700
Data Index: 3193193 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.5784. Min Act: -0.1700
Data Index: 8796880 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.5784. Min Act: -0.1700
Data Index: 6211488 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.5784. Min Act: -0.1700
Data Index: 5773033 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.6097. Min Act: -0.1700
Data Index: 3506754 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.5784. Min Act: -0.1700
Data Index: 4481914 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0472. Min Range: -6.0472
Max Act: 5.5472. Min Act: -0.1700
Data Index: 4759944 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19