Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3444 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.7231. Min Act: -0.1700
Data Index: 5410080 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.5981. Min Act: -0.1700
Data Index: 1094688 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.5981. Min Act: -0.1700
Data Index: 1730762 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.5669. Min Act: -0.1700
Data Index: 5897016 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.5356. Min Act: -0.1700
Data Index: 2665954 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.5356. Min Act: -0.1700
Data Index: 4210383 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.5044. Min Act: -0.1700
Data Index: 4084604 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.5044. Min Act: -0.1700
Data Index: 4081531 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.5044. Min Act: -0.1700
Data Index: 7571552 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.5044. Min Act: -0.1700
Data Index: 7186057 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.5044. Min Act: -0.1700
Data Index: 1769530 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.4106. Min Act: -0.1700
Data Index: 2682087 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.4419. Min Act: -0.1700
Data Index: 7983617 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.4419. Min Act: -0.1700
Data Index: 6088208 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.4419. Min Act: -0.1699
Data Index: 7119793 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.4419. Min Act: -0.1700
Data Index: 2535653 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.4419. Min Act: -0.1700
Data Index: 6841600 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.3794. Min Act: -0.1700
Data Index: 2723812 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.4106. Min Act: -0.1700
Data Index: 3039712 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7231. Min Range: -4.7231
Max Act: 4.4106. Min Act: -0.1700
Data Index: 3094517 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19