Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4082 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4481. Min Range: -5.4481
Max Act: 5.4481. Min Act: -0.1700
Data Index: 7265876 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4481. Min Range: -5.4481
Max Act: 5.4169. Min Act: -0.1700
Data Index: 7000592 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4481. Min Range: -5.4481
Max Act: 5.4169. Min Act: -0.1700
Data Index: 2473462 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4481. Min Range: -5.4481
Max Act: 5.1981. Min Act: -0.1700
Data Index: 1573662 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4481. Min Range: -5.4481
Max Act: 5.1669. Min Act: -0.1700
Data Index: 5167496 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4481. Min Range: -5.4481
Max Act: 5.0419. Min Act: -0.1700
Data Index: 5196773 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4481. Min Range: -5.4481
Max Act: 5.0731. Min Act: -0.1700
Data Index: 155355 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4481. Min Range: -5.4481
Max Act: 5.0731. Min Act: -0.1700
Data Index: 7486877 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4481. Min Range: -5.4481
Max Act: 5.0106. Min Act: -0.1700
Data Index: 3528505 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4481. Min Range: -5.4481
Max Act: 5.0419. Min Act: -0.1700
Data Index: 2737304 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4481. Min Range: -5.4481
Max Act: 5.0106. Min Act: -0.1700
Data Index: 466013 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4481. Min Range: -5.4481
Max Act: 5.0106. Min Act: -0.1700
Data Index: 7048599 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4481. Min Range: -5.4481
Max Act: 4.9794. Min Act: -0.1700
Data Index: 6834283 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4481. Min Range: -5.4481
Max Act: 4.9481. Min Act: -0.1700
Data Index: 4442671 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4481. Min Range: -5.4481
Max Act: 4.9169. Min Act: -0.1700
Data Index: 6718207 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4481. Min Range: -5.4481
Max Act: 4.9481. Min Act: -0.1700
Data Index: 5577139 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4481. Min Range: -5.4481
Max Act: 4.9169. Min Act: -0.1700
Data Index: 4673621 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4481. Min Range: -5.4481
Max Act: 4.9169. Min Act: -0.1700
Data Index: 6412340 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4481. Min Range: -5.4481
Max Act: 4.9169. Min Act: -0.1700
Data Index: 972791 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4481. Min Range: -5.4481
Max Act: 4.8856. Min Act: -0.1700
Data Index: 1641086 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19