Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3239 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.7263. Min Act: -0.1700
Data Index: 3976619 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.6326. Min Act: -0.1700
Data Index: 140977 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.6638. Min Act: -0.1700
Data Index: 3433787 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.6326. Min Act: -0.1700
Data Index: 1922608 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.6326. Min Act: -0.1700
Data Index: 8141600 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.6013. Min Act: -0.1700
Data Index: 2351100 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.6326. Min Act: -0.1700
Data Index: 5318517 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.6326. Min Act: -0.1700
Data Index: 6329428 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.6013. Min Act: -0.1700
Data Index: 2076892 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.6326. Min Act: -0.1700
Data Index: 470515 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.6013. Min Act: -0.1700
Data Index: 1101258 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.6013. Min Act: -0.1700
Data Index: 2061598 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.5701. Min Act: -0.1700
Data Index: 231728 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.5701. Min Act: -0.1700
Data Index: 1185543 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.5701. Min Act: -0.1700
Data Index: 6201537 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.6013. Min Act: -0.1700
Data Index: 7473969 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.5701. Min Act: -0.1700
Data Index: 7455951 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.5388. Min Act: -0.1700
Data Index: 2928004 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.5701. Min Act: -0.1700
Data Index: 340179 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7263. Min Range: -4.7263
Max Act: 4.5701. Min Act: -0.1700
Data Index: 4774975 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19