Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3786 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.2344. Min Act: -0.1700
Data Index: 5955391 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.2013. Min Act: -0.1700
Data Index: 4423507 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.2013. Min Act: -0.1700
Data Index: 3761721 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.2013. Min Act: -0.1700
Data Index: 3927108 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.2013. Min Act: -0.1700
Data Index: 8021687 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1846. Min Act: -0.1700
Data Index: 467899 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1846. Min Act: -0.1700
Data Index: 3450968 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1846. Min Act: -0.1700
Data Index: 1952089 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1846. Min Act: -0.1700
Data Index: 1940862 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1680. Min Act: -0.1700
Data Index: 4595485 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1680. Min Act: -0.1700
Data Index: 4723604 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1514. Min Act: -0.1700
Data Index: 7427143 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1514. Min Act: -0.1700
Data Index: 6290924 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1514. Min Act: -0.1700
Data Index: 3652182 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1680. Min Act: -0.1700
Data Index: 8057565 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1514. Min Act: -0.1700
Data Index: 3995545 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1514. Min Act: -0.1700
Data Index: 6683362 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1514. Min Act: -0.1700
Data Index: 2121406 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1514. Min Act: -0.1700
Data Index: 6592003 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2344. Min Range: -2.2344
Max Act: 2.1514. Min Act: -0.1700
Data Index: 3664371 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19