Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 929 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0429. Min Range: -4.0429
Max Act: 4.0429. Min Act: -0.1700
Data Index: 4515828 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0429. Min Range: -4.0429
Max Act: 4.0116. Min Act: -0.1700
Data Index: 7384005 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0429. Min Range: -4.0429
Max Act: 4.0116. Min Act: -0.1700
Data Index: 1720801 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0429. Min Range: -4.0429
Max Act: 4.0116. Min Act: -0.1699
Data Index: 8113900 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0429. Min Range: -4.0429
Max Act: 4.0116. Min Act: -0.1700
Data Index: 4866598 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.9491. Min Act: -0.1699
Data Index: 4384585 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.9491. Min Act: -0.1700
Data Index: 7715960 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.9491. Min Act: -0.1700
Data Index: 8644495 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.9491. Min Act: -0.1700
Data Index: 4611036 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.9491. Min Act: -0.1700
Data Index: 494986 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.9491. Min Act: -0.1700
Data Index: 4067257 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.8866. Min Act: -0.1698
Data Index: 7018609 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.8553. Min Act: -0.1700
Data Index: 4174676 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.8553. Min Act: -0.1700
Data Index: 2307486 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.8553. Min Act: -0.1699
Data Index: 2333488 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.8553. Min Act: -0.1699
Data Index: 234323 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.8553. Min Act: -0.1700
Data Index: 682681 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.8240. Min Act: -0.1700
Data Index: 2356438 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.8553. Min Act: -0.1699
Data Index: 241396 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0429. Min Range: -4.0429
Max Act: 3.8553. Min Act: -0.1700
Data Index: 2376384 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19