Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0386. Min Range: -6.0386
Max Act: 6.0386. Min Act: -0.1700
Data Index: 1759271 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0386. Min Range: -6.0386
Max Act: 6.0074. Min Act: -0.1700
Data Index: 1452270 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.9449. Min Act: -0.1700
Data Index: 6231278 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.9136. Min Act: -0.1700
Data Index: 8708130 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.9136. Min Act: -0.1700
Data Index: 4711725 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.8511. Min Act: -0.1700
Data Index: 4469757 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.8199. Min Act: -0.1700
Data Index: 2043550 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.7574. Min Act: -0.1700
Data Index: 4126127 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.7261. Min Act: -0.1700
Data Index: 1752472 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.6636. Min Act: -0.1700
Data Index: 4819927 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.6011. Min Act: -0.1700
Data Index: 2906979 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.5386. Min Act: -0.1700
Data Index: 7678216 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.5386. Min Act: -0.1700
Data Index: 4223711 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.5386. Min Act: -0.1700
Data Index: 5853206 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.5386. Min Act: -0.1700
Data Index: 2857995 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.5386. Min Act: -0.1700
Data Index: 6469748 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.5386. Min Act: -0.1700
Data Index: 6252349 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.5386. Min Act: -0.1700
Data Index: 4680835 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.5386. Min Act: -0.1700
Data Index: 4488774 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0386. Min Range: -6.0386
Max Act: 5.5386. Min Act: -0.1700
Data Index: 2445223 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19