Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.6733. Min Act: -0.1700
Data Index: 3374099 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.4546. Min Act: -0.1700
Data Index: 1148443 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.2983. Min Act: -0.1700
Data Index: 6771323 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.2358. Min Act: -0.1700
Data Index: 4506465 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.1733. Min Act: -0.1700
Data Index: 6765818 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.1421. Min Act: -0.1700
Data Index: 4115402 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.1421. Min Act: -0.1700
Data Index: 5100327 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.1421. Min Act: -0.1700
Data Index: 1412855 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.1421. Min Act: -0.1700
Data Index: 3481684 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.1108. Min Act: -0.1700
Data Index: 3395286 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.1108. Min Act: -0.1700
Data Index: 4761806 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.0796. Min Act: -0.1700
Data Index: 6386697 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.0796. Min Act: -0.1700
Data Index: 425146 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.0171. Min Act: -0.1700
Data Index: 8735494 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.0483. Min Act: -0.1700
Data Index: 1862486 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.0483. Min Act: -0.1700
Data Index: 2348124 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.0171. Min Act: -0.1700
Data Index: 3526525 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.0171. Min Act: -0.1700
Data Index: 4374587 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6733. Min Range: -5.6733
Max Act: 5.0171. Min Act: -0.1700
Data Index: 1630075 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6733. Min Range: -5.6733
Max Act: 4.9858. Min Act: -0.1700
Data Index: 6049381 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19