Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2923 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0171. Min Range: -5.0171
Max Act: 5.0171. Min Act: -0.1700
Data Index: 5480304 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.7671. Min Act: -0.1700
Data Index: 750641 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.7359. Min Act: -0.1700
Data Index: 6938839 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.6421. Min Act: -0.1700
Data Index: 1331817 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.6109. Min Act: -0.1700
Data Index: 8680049 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.5484. Min Act: -0.1700
Data Index: 8768045 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.5171. Min Act: -0.1700
Data Index: 5578004 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.5171. Min Act: -0.1700
Data Index: 8166909 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.4859. Min Act: -0.1700
Data Index: 2454670 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.5171. Min Act: -0.1700
Data Index: 7127890 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.4546. Min Act: -0.1700
Data Index: 4031710 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.4546. Min Act: -0.1700
Data Index: 5867415 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.4546. Min Act: -0.1700
Data Index: 2157704 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.4234. Min Act: -0.1700
Data Index: 7789267 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.4234. Min Act: -0.1700
Data Index: 132867 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.4234. Min Act: -0.1700
Data Index: 5801626 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.4234. Min Act: -0.1700
Data Index: 5354619 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.3921. Min Act: -0.1700
Data Index: 1510842 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.3921. Min Act: -0.1700
Data Index: 3812513 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0171. Min Range: -5.0171
Max Act: 4.3609. Min Act: -0.1700
Data Index: 6682478 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19