Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4111 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.6425. Min Act: -0.1700
Data Index: 2037822 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.5016. Min Act: -0.1700
Data Index: 332867 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.4546. Min Act: -0.1700
Data Index: 3322990 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.4390. Min Act: -0.1700
Data Index: 1740162 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.4076. Min Act: -0.1700
Data Index: 1665772 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.3449. Min Act: -0.1700
Data Index: 332873 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.3449. Min Act: -0.1700
Data Index: 5983456 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.3135. Min Act: -0.1700
Data Index: 2812946 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.2978. Min Act: -0.1700
Data Index: 7393852 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.2978. Min Act: -0.1700
Data Index: 320027 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.2507. Min Act: -0.1700
Data Index: 4638533 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.2507. Min Act: -0.1700
Data Index: 6096296 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.2350. Min Act: -0.1700
Data Index: 5396141 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.2193. Min Act: -0.1700
Data Index: 4973097 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.2193. Min Act: -0.1700
Data Index: 7076134 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.1878. Min Act: -0.1700
Data Index: 5306140 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.1563. Min Act: -0.1700
Data Index: 4675829 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.1563. Min Act: -0.1700
Data Index: 1239977 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.1563. Min Act: -0.1700
Data Index: 2412460 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6425. Min Range: -3.6425
Max Act: 3.1091. Min Act: -0.1700
Data Index: 4377074 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19