Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 122 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.7269. Min Act: -0.1700
Data Index: 8826705 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.6332. Min Act: -0.1700
Data Index: 437037 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.5394. Min Act: -0.1700
Data Index: 1766824 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.5082. Min Act: -0.1700
Data Index: 1766817 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.5082. Min Act: -0.1700
Data Index: 4001988 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.4769. Min Act: -0.1700
Data Index: 3775892 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.4769. Min Act: -0.1700
Data Index: 3050768 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.4457. Min Act: -0.1700
Data Index: 5266074 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.4769. Min Act: -0.1700
Data Index: 5072869 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.4144. Min Act: -0.1700
Data Index: 7997520 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.4457. Min Act: -0.1700
Data Index: 3950929 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.4144. Min Act: -0.1700
Data Index: 4889167 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.4144. Min Act: -0.1700
Data Index: 3404866 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.4144. Min Act: -0.1700
Data Index: 441744 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.3832. Min Act: -0.1700
Data Index: 7529340 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.3832. Min Act: -0.1700
Data Index: 7252007 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.3519. Min Act: -0.1700
Data Index: 8439525 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.3519. Min Act: -0.1700
Data Index: 6958824 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.3207. Min Act: -0.1700
Data Index: 6930652 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7269. Min Range: -5.7269
Max Act: 5.3207. Min Act: -0.1700
Data Index: 1655218 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19