Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.6722. Min Act: -0.1700
Data Index: 3016100 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.6410. Min Act: -0.1700
Data Index: 8108372 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.5785. Min Act: -0.1700
Data Index: 54351 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.6097. Min Act: -0.1700
Data Index: 5648786 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.6097. Min Act: -0.1700
Data Index: 8436654 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.5785. Min Act: -0.1700
Data Index: 398511 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.5472. Min Act: -0.1700
Data Index: 7152005 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.6097. Min Act: -0.1700
Data Index: 6591857 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.5160. Min Act: -0.1700
Data Index: 4807629 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.5472. Min Act: -0.1700
Data Index: 6761604 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.5472. Min Act: -0.1700
Data Index: 3697555 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.5160. Min Act: -0.1700
Data Index: 1672607 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.4535. Min Act: -0.1700
Data Index: 4155133 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.4847. Min Act: -0.1700
Data Index: 5916104 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.5160. Min Act: -0.1700
Data Index: 3248487 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.5160. Min Act: -0.1700
Data Index: 2652048 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.4535. Min Act: -0.1700
Data Index: 3724876 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.4535. Min Act: -0.1700
Data Index: 3724875 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.4847. Min Act: -0.1700
Data Index: 2694238 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6722. Min Range: -4.6722
Max Act: 4.5160. Min Act: -0.1700
Data Index: 578248 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19