Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5994 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4555. Min Range: -7.4555
Max Act: 7.4555. Min Act: -0.1700
Data Index: 4533968 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4555. Min Range: -7.4555
Max Act: 7.1118. Min Act: -0.1700
Data Index: 3690339 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4555. Min Range: -7.4555
Max Act: 7.1118. Min Act: -0.1700
Data Index: 1161425 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4555. Min Range: -7.4555
Max Act: 7.0493. Min Act: -0.1700
Data Index: 4533966 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4555. Min Range: -7.4555
Max Act: 7.0493. Min Act: -0.1700
Data Index: 5613479 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4555. Min Range: -7.4555
Max Act: 7.0493. Min Act: -0.1700
Data Index: 4833529 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4555. Min Range: -7.4555
Max Act: 7.0493. Min Act: -0.1700
Data Index: 3356559 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4555. Min Range: -7.4555
Max Act: 7.0180. Min Act: -0.1700
Data Index: 5999735 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4555. Min Range: -7.4555
Max Act: 7.0180. Min Act: -0.1700
Data Index: 1768121 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4555. Min Range: -7.4555
Max Act: 6.9868. Min Act: -0.1700
Data Index: 4833530 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4555. Min Range: -7.4555
Max Act: 6.9555. Min Act: -0.1700
Data Index: 2334438 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4555. Min Range: -7.4555
Max Act: 6.9868. Min Act: -0.1700
Data Index: 4892874 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4555. Min Range: -7.4555
Max Act: 7.0180. Min Act: -0.1700
Data Index: 1337360 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4555. Min Range: -7.4555
Max Act: 6.9555. Min Act: -0.1700
Data Index: 6388556 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4555. Min Range: -7.4555
Max Act: 6.9243. Min Act: -0.1700
Data Index: 6108626 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4555. Min Range: -7.4555
Max Act: 6.9243. Min Act: -0.1700
Data Index: 1443809 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4555. Min Range: -7.4555
Max Act: 6.8930. Min Act: -0.1700
Data Index: 6028118 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4555. Min Range: -7.4555
Max Act: 6.8618. Min Act: -0.1700
Data Index: 5999734 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4555. Min Range: -7.4555
Max Act: 6.7993. Min Act: -0.1700
Data Index: 4533967 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4555. Min Range: -7.4555
Max Act: 6.7993. Min Act: -0.1700
Data Index: 2002123 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19