Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1581 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.9054. Min Act: -0.1700
Data Index: 7794629 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.9054. Min Act: -0.1700
Data Index: 6177590 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.7804. Min Act: -0.1700
Data Index: 1372043 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.7492. Min Act: -0.1700
Data Index: 5483863 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.7492. Min Act: -0.1700
Data Index: 8080835 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.6867. Min Act: -0.1700
Data Index: 890984 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.6554. Min Act: -0.1700
Data Index: 4032032 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.6242. Min Act: -0.1700
Data Index: 4865516 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.6242. Min Act: -0.1700
Data Index: 5958766 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.6554. Min Act: -0.1700
Data Index: 6415836 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.5929. Min Act: -0.1700
Data Index: 4423471 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.5929. Min Act: -0.1700
Data Index: 3429458 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.5617. Min Act: -0.1700
Data Index: 2637193 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.5617. Min Act: -0.1700
Data Index: 8202344 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.5304. Min Act: -0.1700
Data Index: 774526 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.5304. Min Act: -0.1700
Data Index: 1807850 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4992. Min Act: -0.1700
Data Index: 7490503 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4992. Min Act: -0.1700
Data Index: 3084560 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4679. Min Act: -0.1700
Data Index: 1582270 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4992. Min Act: -0.1700
Data Index: 1682894 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19