Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2305 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.5412. Min Act: -0.1700
Data Index: 8135991 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.5098. Min Act: -0.1700
Data Index: 7113728 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.5098. Min Act: -0.1700
Data Index: 4892914 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.4942. Min Act: -0.1700
Data Index: 3329156 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.4315. Min Act: -0.1700
Data Index: 8135992 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.4315. Min Act: -0.1700
Data Index: 8135994 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.4002. Min Act: -0.1700
Data Index: 6582942 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.4002. Min Act: -0.1700
Data Index: 8716777 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.4002. Min Act: -0.1700
Data Index: 363426 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.3688. Min Act: -0.1700
Data Index: 5898648 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.3531. Min Act: -0.1700
Data Index: 929699 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.3688. Min Act: -0.1700
Data Index: 8135996 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.3688. Min Act: -0.1700
Data Index: 8743091 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.3688. Min Act: -0.1700
Data Index: 2076223 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.3688. Min Act: -0.1700
Data Index: 1070029 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.3688. Min Act: -0.1700
Data Index: 2465269 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.3531. Min Act: -0.1700
Data Index: 2676520 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.3688. Min Act: -0.1700
Data Index: 8599650 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.3531. Min Act: -0.1700
Data Index: 8652496 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5412. Min Range: -3.5412
Max Act: 3.3531. Min Act: -0.1700
Data Index: 924298 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19