Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 751 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0303. Min Range: -8.0303
Max Act: 8.0303. Min Act: -0.1700
Data Index: 5523541 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0303. Min Range: -8.0303
Max Act: 8.0303. Min Act: -0.1700
Data Index: 4868348 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0303. Min Range: -8.0303
Max Act: 7.8428. Min Act: -0.1700
Data Index: 2172786 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0303. Min Range: -8.0303
Max Act: 7.7490. Min Act: -0.1700
Data Index: 4501049 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0303. Min Range: -8.0303
Max Act: 7.6865. Min Act: -0.1700
Data Index: 8072088 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0303. Min Range: -8.0303
Max Act: 7.3428. Min Act: -0.1700
Data Index: 2702400 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0303. Min Range: -8.0303
Max Act: 7.2803. Min Act: -0.1700
Data Index: 6691312 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0303. Min Range: -8.0303
Max Act: 7.1553. Min Act: -0.1700
Data Index: 2370101 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0303. Min Range: -8.0303
Max Act: 7.0303. Min Act: -0.1700
Data Index: 707144 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0303. Min Range: -8.0303
Max Act: 7.0615. Min Act: -0.1700
Data Index: 1390280 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0303. Min Range: -8.0303
Max Act: 7.0303. Min Act: -0.1700
Data Index: 6041445 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0303. Min Range: -8.0303
Max Act: 7.0303. Min Act: -0.1700
Data Index: 1372863 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0303. Min Range: -8.0303
Max Act: 7.0303. Min Act: -0.1700
Data Index: 3568750 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0303. Min Range: -8.0303
Max Act: 6.9678. Min Act: -0.1700
Data Index: 8213588 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0303. Min Range: -8.0303
Max Act: 6.9365. Min Act: -0.1700
Data Index: 2951154 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0303. Min Range: -8.0303
Max Act: 6.9365. Min Act: -0.1700
Data Index: 2509147 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0303. Min Range: -8.0303
Max Act: 6.9365. Min Act: -0.1700
Data Index: 1909974 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0303. Min Range: -8.0303
Max Act: 6.9053. Min Act: -0.1700
Data Index: 4575939 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0303. Min Range: -8.0303
Max Act: 6.9053. Min Act: -0.1700
Data Index: 6381044 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0303. Min Range: -8.0303
Max Act: 6.8428. Min Act: -0.1700
Data Index: 5774731 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19