Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3895 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1985. Min Range: -8.1985
Max Act: 8.1985. Min Act: -0.1700
Data Index: 7739810 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1985. Min Range: -8.1985
Max Act: 8.1360. Min Act: -0.1700
Data Index: 1663794 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1985. Min Range: -8.1985
Max Act: 8.1047. Min Act: -0.1700
Data Index: 3145013 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.9172. Min Act: -0.1700
Data Index: 3949982 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.9172. Min Act: -0.1700
Data Index: 8715466 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.8547. Min Act: -0.1700
Data Index: 1415084 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.8547. Min Act: -0.1700
Data Index: 5847452 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.8235. Min Act: -0.1700
Data Index: 4784800 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.8235. Min Act: -0.1700
Data Index: 5970443 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.7922. Min Act: -0.1700
Data Index: 6678854 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.7610. Min Act: -0.1700
Data Index: 1108468 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.7297. Min Act: -0.1700
Data Index: 567438 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.6985. Min Act: -0.1700
Data Index: 8557142 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.6985. Min Act: -0.1700
Data Index: 2886152 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.6985. Min Act: -0.1700
Data Index: 5850671 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.6985. Min Act: -0.1700
Data Index: 6252057 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.6985. Min Act: -0.1700
Data Index: 3529252 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.5735. Min Act: -0.1700
Data Index: 2972093 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.5422. Min Act: -0.1700
Data Index: 4574206 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1985. Min Range: -8.1985
Max Act: 7.5110. Min Act: -0.1700
Data Index: 6557612 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19