Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2171 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.4331. Min Act: -0.1700
Data Index: 6110081 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.4018. Min Act: -0.1700
Data Index: 6772402 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3704. Min Act: -0.1700
Data Index: 4965255 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3704. Min Act: -0.1700
Data Index: 2159886 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3704. Min Act: -0.1700
Data Index: 8639275 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3390. Min Act: -0.1700
Data Index: 5501968 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3390. Min Act: -0.1700
Data Index: 3451052 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3390. Min Act: -0.1700
Data Index: 3167998 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3390. Min Act: -0.1700
Data Index: 1685346 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3390. Min Act: -0.1700
Data Index: 8284798 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3390. Min Act: -0.1700
Data Index: 298502 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3076. Min Act: -0.1700
Data Index: 2101621 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3076. Min Act: -0.1700
Data Index: 965715 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3076. Min Act: -0.1700
Data Index: 42352 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3076. Min Act: -0.1700
Data Index: 286836 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3076. Min Act: -0.1700
Data Index: 2282968 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3076. Min Act: -0.1700
Data Index: 2529445 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3076. Min Act: -0.1700
Data Index: 3346946 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3076. Min Act: -0.1700
Data Index: 1397905 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4331. Min Range: -3.4331
Max Act: 3.3076. Min Act: -0.1700
Data Index: 4691498 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19