Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2565 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.4305. Min Act: -0.1700
Data Index: 583251 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.2118. Min Act: -0.1700
Data Index: 5312470 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.1805. Min Act: -0.1700
Data Index: 3074858 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.1805. Min Act: -0.1700
Data Index: 1439300 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.1493. Min Act: -0.1700
Data Index: 3916349 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.1180. Min Act: -0.1700
Data Index: 6515984 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.1180. Min Act: -0.1700
Data Index: 2325555 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.1493. Min Act: -0.1700
Data Index: 5802764 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.1180. Min Act: -0.1700
Data Index: 4262369 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.1180. Min Act: -0.1700
Data Index: 1439299 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.1180. Min Act: -0.1700
Data Index: 4080655 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.1180. Min Act: -0.1700
Data Index: 7965062 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.1180. Min Act: -0.1700
Data Index: 7006992 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.0867. Min Act: -0.1700
Data Index: 1059794 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.0867. Min Act: -0.1700
Data Index: 4442808 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.0555. Min Act: -0.1700
Data Index: 8612488 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.0555. Min Act: -0.1700
Data Index: 1385097 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.0555. Min Act: -0.1700
Data Index: 8306231 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.0555. Min Act: -0.1700
Data Index: 5492643 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.0555. Min Act: -0.1700
Data Index: 8355311 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19