Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1056 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1115. Min Range: -5.1115
Max Act: 5.1115. Min Act: -0.1700
Data Index: 7473886 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1115. Min Range: -5.1115
Max Act: 5.0490. Min Act: -0.1700
Data Index: 5758135 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.7990. Min Act: -0.1700
Data Index: 3737962 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.7365. Min Act: -0.1700
Data Index: 7560808 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.7053. Min Act: -0.1700
Data Index: 1816639 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.6740. Min Act: -0.1700
Data Index: 4578613 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.5490. Min Act: -0.1700
Data Index: 6888883 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.5803. Min Act: -0.1700
Data Index: 4913441 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.5490. Min Act: -0.1700
Data Index: 8506339 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.5490. Min Act: -0.1700
Data Index: 8626800 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.5490. Min Act: -0.1700
Data Index: 7341230 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.4865. Min Act: -0.1700
Data Index: 4947285 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.5178. Min Act: -0.1700
Data Index: 6570049 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.5178. Min Act: -0.1700
Data Index: 4229107 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.5178. Min Act: -0.1700
Data Index: 4783159 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.4865. Min Act: -0.1700
Data Index: 5901927 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.4553. Min Act: -0.1700
Data Index: 7388728 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.4553. Min Act: -0.1700
Data Index: 820411 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.4553. Min Act: -0.1700
Data Index: 2844152 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1115. Min Range: -5.1115
Max Act: 4.4240. Min Act: -0.1700
Data Index: 2127050 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19