Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4687 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.9555. Min Act: -0.1700
Data Index: 3230878 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.8618. Min Act: -0.1700
Data Index: 7029768 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.8305. Min Act: -0.1700
Data Index: 7705239 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.7680. Min Act: -0.1700
Data Index: 8520840 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.7055. Min Act: -0.1700
Data Index: 7015217 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.6743. Min Act: -0.1700
Data Index: 5002003 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.6118. Min Act: -0.1700
Data Index: 1241147 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.5805. Min Act: -0.1700
Data Index: 6502063 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.5493. Min Act: -0.1700
Data Index: 4079206 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.5493. Min Act: -0.1700
Data Index: 7298310 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.4868. Min Act: -0.1700
Data Index: 3839786 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.4868. Min Act: -0.1700
Data Index: 8293483 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.4868. Min Act: -0.1700
Data Index: 4547984 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.4243. Min Act: -0.1700
Data Index: 4325848 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.4555. Min Act: -0.1700
Data Index: 1174540 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.3930. Min Act: -0.1700
Data Index: 3304523 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.3618. Min Act: -0.1700
Data Index: 1178562 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.3618. Min Act: -0.1700
Data Index: 1217329 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.3305. Min Act: -0.1700
Data Index: 986558 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9555. Min Range: -7.9555
Max Act: 7.3618. Min Act: -0.1700
Data Index: 5960544 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19