Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2955 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2858. Min Range: -5.2858
Max Act: 5.2858. Min Act: -0.1700
Data Index: 4652178 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2858. Min Range: -5.2858
Max Act: 5.1608. Min Act: -0.1700
Data Index: 5374352 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2858. Min Range: -5.2858
Max Act: 5.1295. Min Act: -0.1700
Data Index: 7897985 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2858. Min Range: -5.2858
Max Act: 5.1295. Min Act: -0.1700
Data Index: 632029 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.9733. Min Act: -0.1700
Data Index: 5937134 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.9733. Min Act: -0.1700
Data Index: 1026601 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.9420. Min Act: -0.1700
Data Index: 1710872 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.9420. Min Act: -0.1700
Data Index: 7645730 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.8795. Min Act: -0.1700
Data Index: 4628140 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.8170. Min Act: -0.1700
Data Index: 1647206 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.8170. Min Act: -0.1700
Data Index: 1066026 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.8170. Min Act: -0.1700
Data Index: 5424686 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.8483. Min Act: -0.1700
Data Index: 1340488 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.7858. Min Act: -0.1700
Data Index: 7779807 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.7858. Min Act: -0.1700
Data Index: 4925730 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.7858. Min Act: -0.1700
Data Index: 6251556 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.7545. Min Act: -0.1700
Data Index: 5922129 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.7858. Min Act: -0.1700
Data Index: 8160280 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.7858. Min Act: -0.1700
Data Index: 643523 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2858. Min Range: -5.2858
Max Act: 4.7858. Min Act: -0.1700
Data Index: 6069049 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19