Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.4336. Min Act: -0.1700
Data Index: 6774411 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.4336. Min Act: -0.1700
Data Index: 5147810 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.3711. Min Act: -0.1700
Data Index: 6581544 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.3398. Min Act: -0.1700
Data Index: 8062275 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.3398. Min Act: -0.1700
Data Index: 5924982 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.3398. Min Act: -0.1700
Data Index: 4161252 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.3086. Min Act: -0.1700
Data Index: 6003605 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.3086. Min Act: -0.1700
Data Index: 6986652 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.3086. Min Act: -0.1700
Data Index: 2458658 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.3086. Min Act: -0.1700
Data Index: 6675393 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.3086. Min Act: -0.1700
Data Index: 1296773 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.2773. Min Act: -0.1700
Data Index: 536035 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.2773. Min Act: -0.1700
Data Index: 453484 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.3086. Min Act: -0.1700
Data Index: 445763 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.2773. Min Act: -0.1700
Data Index: 7296163 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.2773. Min Act: -0.1700
Data Index: 7736633 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.2773. Min Act: -0.1700
Data Index: 1780184 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.2773. Min Act: -0.1700
Data Index: 1895285 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.2773. Min Act: -0.1700
Data Index: 6634838 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4336. Min Range: -5.4336
Max Act: 5.2461. Min Act: -0.1700
Data Index: 745210 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19