Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2680 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.7522. Min Act: -0.1700
Data Index: 2282702 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.7834. Min Act: -0.1700
Data Index: 2361871 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.7834. Min Act: -0.1700
Data Index: 5881298 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.7522. Min Act: -0.1700
Data Index: 3722313 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.7522. Min Act: -0.1700
Data Index: 718772 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.6897. Min Act: -0.1700
Data Index: 2579707 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.6897. Min Act: -0.1700
Data Index: 3399193 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.6584. Min Act: -0.1700
Data Index: 140883 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.6897. Min Act: -0.1700
Data Index: 598456 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.6584. Min Act: -0.1700
Data Index: 33648 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.5959. Min Act: -0.1700
Data Index: 3999506 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.5959. Min Act: -0.1700
Data Index: 3208127 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.5647. Min Act: -0.1700
Data Index: 1419562 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.5959. Min Act: -0.1700
Data Index: 5417529 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.5647. Min Act: -0.1700
Data Index: 7599903 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.5334. Min Act: -0.1700
Data Index: 7482604 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.5022. Min Act: -0.1700
Data Index: 1360338 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.5022. Min Act: -0.1700
Data Index: 599980 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.4397. Min Act: -0.1700
Data Index: 3202005 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7834. Min Range: -7.7834
Max Act: 7.4709. Min Act: -0.1700
Data Index: 6431488 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19