Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5964 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.6106. Min Act: -0.1700
Data Index: 1647397 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.5481. Min Act: -0.1700
Data Index: 6886768 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.6106. Min Act: -0.1700
Data Index: 1432242 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.3606. Min Act: -0.1700
Data Index: 7675698 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.2981. Min Act: -0.1700
Data Index: 2034100 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.2981. Min Act: -0.1700
Data Index: 8147552 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.2356. Min Act: -0.1700
Data Index: 3657447 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.2356. Min Act: -0.1700
Data Index: 6138122 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.1731. Min Act: -0.1700
Data Index: 4539522 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.1731. Min Act: -0.1700
Data Index: 3907266 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.1731. Min Act: -0.1700
Data Index: 8222511 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.1731. Min Act: -0.1700
Data Index: 5633818 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.2356. Min Act: -0.1700
Data Index: 2128226 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.1731. Min Act: -0.1700
Data Index: 5485140 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.1731. Min Act: -0.1700
Data Index: 2448792 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.1731. Min Act: -0.1700
Data Index: 7041636 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.1106. Min Act: -0.1698
Data Index: 1362336 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.1731. Min Act: -0.1700
Data Index: 5702066 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.1731. Min Act: -0.1700
Data Index: 4312565 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6106. Min Range: -8.6106
Max Act: 8.1106. Min Act: -0.1700
Data Index: 2249816 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19