Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3619 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6083. Min Range: -7.6083
Max Act: 7.6083. Min Act: -0.1700
Data Index: 2548645 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6083. Min Range: -7.6083
Max Act: 7.3583. Min Act: -0.1700
Data Index: 8779222 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6083. Min Range: -7.6083
Max Act: 7.2958. Min Act: -0.1700
Data Index: 3948595 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6083. Min Range: -7.6083
Max Act: 7.2021. Min Act: -0.1700
Data Index: 5408488 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6083. Min Range: -7.6083
Max Act: 7.1708. Min Act: -0.1700
Data Index: 1845085 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6083. Min Range: -7.6083
Max Act: 7.1396. Min Act: -0.1700
Data Index: 8188637 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6083. Min Range: -7.6083
Max Act: 7.0771. Min Act: -0.1700
Data Index: 2111254 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6083. Min Range: -7.6083
Max Act: 7.1083. Min Act: -0.1700
Data Index: 4858440 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6083. Min Range: -7.6083
Max Act: 7.0771. Min Act: -0.1700
Data Index: 6217833 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6083. Min Range: -7.6083
Max Act: 6.9833. Min Act: -0.1700
Data Index: 4038749 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6083. Min Range: -7.6083
Max Act: 6.9833. Min Act: -0.1700
Data Index: 4194675 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6083. Min Range: -7.6083
Max Act: 6.9521. Min Act: -0.1700
Data Index: 3761036 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6083. Min Range: -7.6083
Max Act: 6.9521. Min Act: -0.1700
Data Index: 2366271 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6083. Min Range: -7.6083
Max Act: 6.9208. Min Act: -0.1700
Data Index: 568732 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6083. Min Range: -7.6083
Max Act: 6.8896. Min Act: -0.1700
Data Index: 8012271 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6083. Min Range: -7.6083
Max Act: 6.9208. Min Act: -0.1700
Data Index: 3472223 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6083. Min Range: -7.6083
Max Act: 6.8896. Min Act: -0.1700
Data Index: 4222294 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6083. Min Range: -7.6083
Max Act: 6.8583. Min Act: -0.1700
Data Index: 710553 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6083. Min Range: -7.6083
Max Act: 6.8583. Min Act: -0.1700
Data Index: 1893993 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6083. Min Range: -7.6083
Max Act: 6.8583. Min Act: -0.1700
Data Index: 6073899 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19