Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2721 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6243. Min Range: -7.6243
Max Act: 7.6243. Min Act: -0.1700
Data Index: 2142276 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6243. Min Range: -7.6243
Max Act: 7.5306. Min Act: -0.1700
Data Index: 7618113 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6243. Min Range: -7.6243
Max Act: 7.5306. Min Act: -0.1700
Data Index: 2142277 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6243. Min Range: -7.6243
Max Act: 7.4368. Min Act: -0.1700
Data Index: 3106200 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6243. Min Range: -7.6243
Max Act: 7.2181. Min Act: -0.1700
Data Index: 3555376 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6243. Min Range: -7.6243
Max Act: 7.1243. Min Act: -0.1700
Data Index: 3975975 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6243. Min Range: -7.6243
Max Act: 7.0931. Min Act: -0.1700
Data Index: 3193016 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6243. Min Range: -7.6243
Max Act: 7.0306. Min Act: -0.1700
Data Index: 7296290 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6243. Min Range: -7.6243
Max Act: 6.9993. Min Act: -0.1700
Data Index: 6436581 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6243. Min Range: -7.6243
Max Act: 6.9368. Min Act: -0.1700
Data Index: 885134 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6243. Min Range: -7.6243
Max Act: 6.9681. Min Act: -0.1700
Data Index: 5786565 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6243. Min Range: -7.6243
Max Act: 6.9681. Min Act: -0.1700
Data Index: 1135551 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6243. Min Range: -7.6243
Max Act: 6.9681. Min Act: -0.1700
Data Index: 4088729 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6243. Min Range: -7.6243
Max Act: 6.9368. Min Act: -0.1700
Data Index: 5534914 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6243. Min Range: -7.6243
Max Act: 6.9368. Min Act: -0.1700
Data Index: 698744 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6243. Min Range: -7.6243
Max Act: 6.9056. Min Act: -0.1700
Data Index: 1309552 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6243. Min Range: -7.6243
Max Act: 6.9056. Min Act: -0.1700
Data Index: 5737591 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6243. Min Range: -7.6243
Max Act: 6.9056. Min Act: -0.1700
Data Index: 3557566 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6243. Min Range: -7.6243
Max Act: 6.8743. Min Act: -0.1700
Data Index: 635039 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6243. Min Range: -7.6243
Max Act: 6.8743. Min Act: -0.1700
Data Index: 5672924 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19