Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 826 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1392. Min Range: -3.1392
Max Act: 3.1392. Min Act: -0.1700
Data Index: 2602549 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1392. Min Range: -3.1392
Max Act: 3.0762. Min Act: -0.1700
Data Index: 5462375 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1392. Min Range: -3.1392
Max Act: 3.0604. Min Act: -0.1700
Data Index: 5486190 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1392. Min Range: -3.1392
Max Act: 3.0446. Min Act: -0.1700
Data Index: 397376 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1392. Min Range: -3.1392
Max Act: 3.0130. Min Act: -0.1700
Data Index: 8452958 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1392. Min Range: -3.1392
Max Act: 3.0130. Min Act: -0.1700
Data Index: 5720376 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1392. Min Range: -3.1392
Max Act: 3.0130. Min Act: -0.1700
Data Index: 7733423 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1392. Min Range: -3.1392
Max Act: 2.9814. Min Act: -0.1700
Data Index: 7073044 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1392. Min Range: -3.1392
Max Act: 2.9656. Min Act: -0.1700
Data Index: 4518104 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1392. Min Range: -3.1392
Max Act: 2.9656. Min Act: -0.1700
Data Index: 4509542 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1392. Min Range: -3.1392
Max Act: 2.9656. Min Act: -0.1700
Data Index: 8218171 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1392. Min Range: -3.1392
Max Act: 2.9814. Min Act: -0.1700
Data Index: 4496115 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1392. Min Range: -3.1392
Max Act: 2.9656. Min Act: -0.1700
Data Index: 4698050 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1392. Min Range: -3.1392
Max Act: 2.9339. Min Act: -0.1700
Data Index: 4318917 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1392. Min Range: -3.1392
Max Act: 2.9339. Min Act: -0.1700
Data Index: 8290137 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1392. Min Range: -3.1392
Max Act: 2.9339. Min Act: -0.1700
Data Index: 1711819 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1392. Min Range: -3.1392
Max Act: 2.9339. Min Act: -0.1700
Data Index: 5963250 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1392. Min Range: -3.1392
Max Act: 2.9339. Min Act: -0.1700
Data Index: 8208459 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1392. Min Range: -3.1392
Max Act: 2.9339. Min Act: -0.1700
Data Index: 1488465 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1392. Min Range: -3.1392
Max Act: 2.9022. Min Act: -0.1700
Data Index: 6350328 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19