Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4254 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2441. Min Range: -6.2441
Max Act: 6.2441. Min Act: -0.1700
Data Index: 2205188 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2441. Min Range: -6.2441
Max Act: 6.1816. Min Act: -0.1700
Data Index: 1894405 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2441. Min Range: -6.2441
Max Act: 6.1816. Min Act: -0.1700
Data Index: 4553726 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2441. Min Range: -6.2441
Max Act: 6.1816. Min Act: -0.1700
Data Index: 8316864 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2441. Min Range: -6.2441
Max Act: 6.1191. Min Act: -0.1700
Data Index: 940061 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2441. Min Range: -6.2441
Max Act: 6.1191. Min Act: -0.1700
Data Index: 4553723 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2441. Min Range: -6.2441
Max Act: 6.0253. Min Act: -0.1700
Data Index: 192659 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2441. Min Range: -6.2441
Max Act: 6.0566. Min Act: -0.1700
Data Index: 2205185 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2441. Min Range: -6.2441
Max Act: 6.0253. Min Act: -0.1700
Data Index: 7302114 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2441. Min Range: -6.2441
Max Act: 6.0253. Min Act: -0.1700
Data Index: 2196519 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2441. Min Range: -6.2441
Max Act: 5.9941. Min Act: -0.1700
Data Index: 4067944 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2441. Min Range: -6.2441
Max Act: 5.9941. Min Act: -0.1700
Data Index: 4553729 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2441. Min Range: -6.2441
Max Act: 5.9941. Min Act: -0.1700
Data Index: 945433 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2441. Min Range: -6.2441
Max Act: 5.9941. Min Act: -0.1700
Data Index: 2205191 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2441. Min Range: -6.2441
Max Act: 5.9941. Min Act: -0.1700
Data Index: 6613907 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2441. Min Range: -6.2441
Max Act: 5.9628. Min Act: -0.1700
Data Index: 1328731 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2441. Min Range: -6.2441
Max Act: 5.9628. Min Act: -0.1700
Data Index: 4042911 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2441. Min Range: -6.2441
Max Act: 5.9316. Min Act: -0.1700
Data Index: 3006994 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2441. Min Range: -6.2441
Max Act: 5.9941. Min Act: -0.1700
Data Index: 70656 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2441. Min Range: -6.2441
Max Act: 5.9628. Min Act: -0.1700
Data Index: 1416497 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19