Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3877 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.2908. Min Act: -0.1700
Data Index: 1612047 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.2908. Min Act: -0.1700
Data Index: 6747527 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.2908. Min Act: -0.1700
Data Index: 5799895 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.2908. Min Act: -0.1700
Data Index: 3988097 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.2596. Min Act: -0.1700
Data Index: 3805070 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.2283. Min Act: -0.1700
Data Index: 5637418 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.2283. Min Act: -0.1700
Data Index: 5578404 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.2283. Min Act: -0.1700
Data Index: 939435 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.1971. Min Act: -0.1700
Data Index: 1174029 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.1658. Min Act: -0.1700
Data Index: 2358946 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.1971. Min Act: -0.1700
Data Index: 3392148 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.1346. Min Act: -0.1700
Data Index: 3738648 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.1346. Min Act: -0.1700
Data Index: 5112036 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.1658. Min Act: -0.1700
Data Index: 8829666 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.1658. Min Act: -0.1700
Data Index: 4217670 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.1658. Min Act: -0.1700
Data Index: 6846572 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.1346. Min Act: -0.1700
Data Index: 263484 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.1346. Min Act: -0.1700
Data Index: 5706683 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.1033. Min Act: -0.1700
Data Index: 1223140 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2908. Min Range: -5.2908
Max Act: 5.1033. Min Act: -0.1700
Data Index: 3214488 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19