Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3817 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0292. Min Range: -5.0292
Max Act: 5.0292. Min Act: -0.1700
Data Index: 5782190 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.8104. Min Act: -0.1700
Data Index: 1397356 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.6854. Min Act: -0.1700
Data Index: 7830906 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.5917. Min Act: -0.1700
Data Index: 4271216 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.5917. Min Act: -0.1700
Data Index: 7085448 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.5604. Min Act: -0.1700
Data Index: 6273643 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.5292. Min Act: -0.1700
Data Index: 2611594 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.5292. Min Act: -0.1700
Data Index: 6756999 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.5292. Min Act: -0.1700
Data Index: 679516 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.4667. Min Act: -0.1700
Data Index: 234582 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.4979. Min Act: -0.1700
Data Index: 5273277 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.4979. Min Act: -0.1700
Data Index: 2611595 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.4354. Min Act: -0.1700
Data Index: 915421 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.4354. Min Act: -0.1700
Data Index: 4930504 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.4354. Min Act: -0.1700
Data Index: 1851892 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.4354. Min Act: -0.1700
Data Index: 621566 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.4042. Min Act: -0.1700
Data Index: 6350263 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.4042. Min Act: -0.1700
Data Index: 679517 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.4042. Min Act: -0.1700
Data Index: 4646739 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0292. Min Range: -5.0292
Max Act: 4.4042. Min Act: -0.1700
Data Index: 5995049 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19