Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1926 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.2288. Min Act: -0.1700
Data Index: 1466006 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.2200. Min Act: -0.1700
Data Index: 3628980 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.1848. Min Act: -0.1700
Data Index: 7950824 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.1848. Min Act: -0.1700
Data Index: 34442 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.1408. Min Act: -0.1700
Data Index: 3366223 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.1408. Min Act: -0.1700
Data Index: 2650709 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.1496. Min Act: -0.1699
Data Index: 8572609 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.1408. Min Act: -0.1700
Data Index: 4997842 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.1320. Min Act: -0.1700
Data Index: 4859905 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.1145. Min Act: -0.1700
Data Index: 4680999 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.1320. Min Act: -0.1700
Data Index: 6198244 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.1145. Min Act: -0.1700
Data Index: 1966259 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.1057. Min Act: -0.1700
Data Index: 717365 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.0707. Min Act: -0.1699
Data Index: 5414274 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.0532. Min Act: -0.1700
Data Index: 4931066 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.0532. Min Act: -0.1700
Data Index: 3314599 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.0532. Min Act: -0.1700
Data Index: 3829176 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.0532. Min Act: -0.1700
Data Index: 1142631 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.0445. Min Act: -0.1700
Data Index: 2746935 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2288. Min Range: -1.2288
Max Act: 1.0445. Min Act: -0.1700
Data Index: 6474899 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19