Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 546 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6229. Min Range: -7.6229
Max Act: 7.6229. Min Act: -0.1700
Data Index: 8358577 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6229. Min Range: -7.6229
Max Act: 7.5604. Min Act: -0.1700
Data Index: 8358575 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6229. Min Range: -7.6229
Max Act: 7.3104. Min Act: -0.1700
Data Index: 8358580 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6229. Min Range: -7.6229
Max Act: 7.1542. Min Act: -0.1700
Data Index: 2388615 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.9979. Min Act: -0.1700
Data Index: 2584957 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.9667. Min Act: -0.1700
Data Index: 7520821 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.9354. Min Act: -0.1700
Data Index: 3491963 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.8417. Min Act: -0.1700
Data Index: 344409 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.8417. Min Act: -0.1700
Data Index: 8452605 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.7792. Min Act: -0.1700
Data Index: 3359655 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.7792. Min Act: -0.1700
Data Index: 1277329 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.7479. Min Act: -0.1700
Data Index: 3669939 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.7479. Min Act: -0.1700
Data Index: 1373368 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.7479. Min Act: -0.1700
Data Index: 7305961 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.7479. Min Act: -0.1700
Data Index: 7834746 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.6854. Min Act: -0.1700
Data Index: 4212205 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.7167. Min Act: -0.1700
Data Index: 309871 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.7167. Min Act: -0.1700
Data Index: 6283441 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.6542. Min Act: -0.1700
Data Index: 3472631 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6229. Min Range: -7.6229
Max Act: 6.6854. Min Act: -0.1700
Data Index: 2140737 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19