Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2494 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.2705. Min Act: -0.1700
Data Index: 6341241 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.1210. Min Act: -0.1700
Data Index: 3863282 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.1043. Min Act: -0.1700
Data Index: 6197032 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0876. Min Act: -0.1700
Data Index: 7312789 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0708. Min Act: -0.1700
Data Index: 23116 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0708. Min Act: -0.1700
Data Index: 5019949 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0540. Min Act: -0.1700
Data Index: 1456532 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0540. Min Act: -0.1700
Data Index: 309372 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0708. Min Act: -0.1700
Data Index: 6041515 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0540. Min Act: -0.1700
Data Index: 3254165 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0540. Min Act: -0.1700
Data Index: 3103781 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0540. Min Act: -0.1700
Data Index: 8750744 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0372. Min Act: -0.1700
Data Index: 4928343 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0372. Min Act: -0.1700
Data Index: 8258859 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0372. Min Act: -0.1700
Data Index: 7833404 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0372. Min Act: -0.1700
Data Index: 3224243 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0372. Min Act: -0.1700
Data Index: 7673719 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0203. Min Act: -0.1700
Data Index: 7248202 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0203. Min Act: -0.1700
Data Index: 2849765 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2705. Min Range: -2.2705
Max Act: 2.0034. Min Act: -0.1700
Data Index: 605524 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19