Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3805 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.7304. Min Act: -0.1700
Data Index: 554790 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.6992. Min Act: -0.1700
Data Index: 7873236 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.6679. Min Act: -0.1700
Data Index: 7603869 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.6367. Min Act: -0.1700
Data Index: 571004 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.6367. Min Act: -0.1700
Data Index: 319055 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.6367. Min Act: -0.1700
Data Index: 7456380 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.6054. Min Act: -0.1700
Data Index: 7203322 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.6054. Min Act: -0.1700
Data Index: 835560 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.5742. Min Act: -0.1700
Data Index: 6457646 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.5742. Min Act: -0.1700
Data Index: 2052822 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.5429. Min Act: -0.1700
Data Index: 3754019 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.5429. Min Act: -0.1700
Data Index: 3266580 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.5429. Min Act: -0.1700
Data Index: 7456383 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.5742. Min Act: -0.1700
Data Index: 1754938 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.5117. Min Act: -0.1700
Data Index: 8745507 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.5117. Min Act: -0.1700
Data Index: 574794 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.5117. Min Act: -0.1700
Data Index: 8640877 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.5117. Min Act: -0.1700
Data Index: 7115773 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.4804. Min Act: -0.1700
Data Index: 6758919 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.4804. Min Act: -0.1700
Data Index: 7456385 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19