Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.8197. Min Act: -0.1700
Data Index: 5041502 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.6322. Min Act: -0.1700
Data Index: 3220056 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.6009. Min Act: -0.1700
Data Index: 3295682 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.6322. Min Act: -0.1700
Data Index: 8165151 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.5697. Min Act: -0.1700
Data Index: 3335956 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.5697. Min Act: -0.1700
Data Index: 5316688 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.5697. Min Act: -0.1700
Data Index: 6610922 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.5697. Min Act: -0.1700
Data Index: 3422326 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.5384. Min Act: -0.1700
Data Index: 3566542 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.5384. Min Act: -0.1700
Data Index: 7061574 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.5384. Min Act: -0.1700
Data Index: 4499814 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.5072. Min Act: -0.1700
Data Index: 1729946 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.5072. Min Act: -0.1700
Data Index: 8360802 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.5072. Min Act: -0.1700
Data Index: 4651356 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.5072. Min Act: -0.1700
Data Index: 5302534 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.4759. Min Act: -0.1700
Data Index: 6059883 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.4759. Min Act: -0.1700
Data Index: 2351368 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.4759. Min Act: -0.1700
Data Index: 7169343 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.4759. Min Act: -0.1700
Data Index: 3405016 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8197. Min Range: -5.8197
Max Act: 5.4759. Min Act: -0.1700
Data Index: 3051751 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19