Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5580 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.0199. Min Range: -13.0199
Max Act: 13.0199. Min Act: -0.1700
Data Index: 5208025 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0199. Min Range: -13.0199
Max Act: 12.8324. Min Act: -0.1700
Data Index: 962414 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.8949. Min Act: -0.1700
Data Index: 2281871 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.8949. Min Act: -0.1700
Data Index: 1889719 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.7699. Min Act: -0.1700
Data Index: 471773 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.7699. Min Act: -0.1700
Data Index: 8566689 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.8324. Min Act: -0.1700
Data Index: 2346073 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.8324. Min Act: -0.1700
Data Index: 2746972 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.7699. Min Act: -0.1700
Data Index: 1027919 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.7699. Min Act: -0.1700
Data Index: 7223412 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.6449. Min Act: -0.1700
Data Index: 4807706 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.5824. Min Act: -0.1700
Data Index: 1700152 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.3949. Min Act: -0.1700
Data Index: 3977170 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.4574. Min Act: -0.1700
Data Index: 7998886 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.4574. Min Act: -0.1700
Data Index: 7471554 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.4574. Min Act: -0.1700
Data Index: 4271406 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.3949. Min Act: -0.1700
Data Index: 8779018 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.3324. Min Act: -0.1700
Data Index: 3745072 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.2074. Min Act: -0.1700
Data Index: 1875145 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0199. Min Range: -13.0199
Max Act: 11.1449. Min Act: -0.1700
Data Index: 5555409 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19