Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.7144. Min Act: -0.1700
Data Index: 4910536 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.7456. Min Act: -0.1700
Data Index: 2549323 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.6519. Min Act: -0.1700
Data Index: 8762906 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.7144. Min Act: -0.1700
Data Index: 2192329 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.6206. Min Act: -0.1700
Data Index: 7560856 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.6206. Min Act: -0.1700
Data Index: 5710048 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.5894. Min Act: -0.1700
Data Index: 5754524 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.5894. Min Act: -0.1700
Data Index: 7560853 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.5894. Min Act: -0.1700
Data Index: 329539 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.5581. Min Act: -0.1700
Data Index: 78538 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.5269. Min Act: -0.1700
Data Index: 7691477 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.4956. Min Act: -0.1700
Data Index: 5340389 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.4956. Min Act: -0.1700
Data Index: 5366286 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.4644. Min Act: -0.1700
Data Index: 1068032 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.4644. Min Act: -0.1700
Data Index: 7268404 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.4956. Min Act: -0.1700
Data Index: 555044 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.4644. Min Act: -0.1700
Data Index: 1323509 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.4956. Min Act: -0.1700
Data Index: 3628306 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.4644. Min Act: -0.1700
Data Index: 8223234 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7456. Min Range: -4.7456
Max Act: 4.4956. Min Act: -0.1700
Data Index: 4207569 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19