Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1049 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0683. Min Range: -11.0683
Max Act: 11.0683. Min Act: -0.1700
Data Index: 4749732 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0683. Min Range: -11.0683
Max Act: 11.0058. Min Act: -0.1700
Data Index: 7787432 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.8808. Min Act: -0.1700
Data Index: 3487944 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.8183. Min Act: -0.1700
Data Index: 1734091 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.7558. Min Act: -0.1700
Data Index: 6423484 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.6933. Min Act: -0.1700
Data Index: 7659382 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.6308. Min Act: -0.1700
Data Index: 765561 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.5683. Min Act: -0.1700
Data Index: 5721881 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.5683. Min Act: -0.1700
Data Index: 1897584 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.5683. Min Act: -0.1700
Data Index: 3625095 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.5058. Min Act: -0.1700
Data Index: 2229292 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.4433. Min Act: -0.1700
Data Index: 2403608 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.5058. Min Act: -0.1700
Data Index: 7150109 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.5058. Min Act: -0.1700
Data Index: 2778937 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.5683. Min Act: -0.1700
Data Index: 3682456 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.4433. Min Act: -0.1700
Data Index: 2086839 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.4433. Min Act: -0.1700
Data Index: 999287 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.4433. Min Act: -0.1700
Data Index: 2282807 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.4433. Min Act: -0.1700
Data Index: 1214258 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0683. Min Range: -11.0683
Max Act: 10.3808. Min Act: -0.1700
Data Index: 7502165 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19