Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5664 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0083. Min Range: -5.0083
Max Act: 5.0083. Min Act: -0.1700
Data Index: 4297302 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.9145. Min Act: -0.1700
Data Index: 8257506 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.8833. Min Act: -0.1700
Data Index: 6643015 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.8520. Min Act: -0.1700
Data Index: 6665701 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.8208. Min Act: -0.1700
Data Index: 3298219 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.7895. Min Act: -0.1700
Data Index: 7361721 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.7895. Min Act: -0.1700
Data Index: 2185880 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.7583. Min Act: -0.1700
Data Index: 1556414 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.7583. Min Act: -0.1700
Data Index: 167224 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.7270. Min Act: -0.1700
Data Index: 365849 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.7270. Min Act: -0.1700
Data Index: 7798022 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.7270. Min Act: -0.1700
Data Index: 5249667 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.7583. Min Act: -0.1700
Data Index: 7273123 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.7270. Min Act: -0.1700
Data Index: 4449009 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.7270. Min Act: -0.1700
Data Index: 8162540 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.6958. Min Act: -0.1700
Data Index: 3875289 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.6645. Min Act: -0.1700
Data Index: 4921600 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.6645. Min Act: -0.1700
Data Index: 6602843 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.6645. Min Act: -0.1700
Data Index: 838772 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0083. Min Range: -5.0083
Max Act: 4.6645. Min Act: -0.1700
Data Index: 944342 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19