Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3696 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.7411. Min Act: -0.1700
Data Index: 5486961 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.5377. Min Act: -0.1700
Data Index: 3746517 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.4594. Min Act: -0.1700
Data Index: 1698753 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.4750. Min Act: -0.1700
Data Index: 3510178 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.3967. Min Act: -0.1700
Data Index: 1313370 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.4123. Min Act: -0.1700
Data Index: 5191211 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.3339. Min Act: -0.1700
Data Index: 1450428 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.3339. Min Act: -0.1700
Data Index: 5031047 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.3339. Min Act: -0.1700
Data Index: 7095084 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.3182. Min Act: -0.1700
Data Index: 4235997 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.3339. Min Act: -0.1700
Data Index: 2134849 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.3025. Min Act: -0.1700
Data Index: 6995311 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.2868. Min Act: -0.1700
Data Index: 3395604 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.2868. Min Act: -0.1700
Data Index: 2059107 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.2868. Min Act: -0.1700
Data Index: 8498809 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.2554. Min Act: -0.1700
Data Index: 5676504 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.2554. Min Act: -0.1700
Data Index: 6731063 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.2397. Min Act: -0.1700
Data Index: 8251941 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.2397. Min Act: -0.1700
Data Index: 4862092 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7411. Min Range: -3.7411
Max Act: 3.2397. Min Act: -0.1700
Data Index: 3381530 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19