Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 476 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.7647. Min Act: -0.1700
Data Index: 6695499 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.7022. Min Act: -0.1700
Data Index: 3780636 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.6397. Min Act: -0.1700
Data Index: 2026708 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.5460. Min Act: -0.1700
Data Index: 8353846 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.5147. Min Act: -0.1700
Data Index: 2073095 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4835. Min Act: -0.1700
Data Index: 1326100 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4835. Min Act: -0.1700
Data Index: 8111488 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4835. Min Act: -0.1700
Data Index: 6668140 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4522. Min Act: -0.1700
Data Index: 3405177 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4522. Min Act: -0.1700
Data Index: 2561726 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4522. Min Act: -0.1700
Data Index: 5364258 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4522. Min Act: -0.1700
Data Index: 7505460 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4522. Min Act: -0.1700
Data Index: 8779357 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4522. Min Act: -0.1700
Data Index: 3265847 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4522. Min Act: -0.1700
Data Index: 3129126 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4522. Min Act: -0.1700
Data Index: 6388973 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4210. Min Act: -0.1700
Data Index: 4785923 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4210. Min Act: -0.1700
Data Index: 2823882 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4522. Min Act: -0.1700
Data Index: 2561720 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7647. Min Range: -4.7647
Max Act: 4.4210. Min Act: -0.1700
Data Index: 6085553 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19