Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3207 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4528. Min Range: -5.4528
Max Act: 5.4528. Min Act: -0.1700
Data Index: 8488661 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4528. Min Range: -5.4528
Max Act: 5.2966. Min Act: -0.1700
Data Index: 6782431 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4528. Min Range: -5.4528
Max Act: 5.1403. Min Act: -0.1700
Data Index: 1144214 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4528. Min Range: -5.4528
Max Act: 5.0778. Min Act: -0.1700
Data Index: 7277504 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4528. Min Range: -5.4528
Max Act: 5.0153. Min Act: -0.1700
Data Index: 3883040 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4528. Min Range: -5.4528
Max Act: 5.0153. Min Act: -0.1700
Data Index: 3898790 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4528. Min Range: -5.4528
Max Act: 4.8591. Min Act: -0.1700
Data Index: 4174138 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4528. Min Range: -5.4528
Max Act: 4.8591. Min Act: -0.1700
Data Index: 8397178 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4528. Min Range: -5.4528
Max Act: 4.8591. Min Act: -0.1700
Data Index: 5715427 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4528. Min Range: -5.4528
Max Act: 4.8278. Min Act: -0.1700
Data Index: 8829809 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4528. Min Range: -5.4528
Max Act: 4.8278. Min Act: -0.1700
Data Index: 6998522 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4528. Min Range: -5.4528
Max Act: 4.8278. Min Act: -0.1700
Data Index: 1683758 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4528. Min Range: -5.4528
Max Act: 4.7966. Min Act: -0.1700
Data Index: 2194872 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4528. Min Range: -5.4528
Max Act: 4.7966. Min Act: -0.1700
Data Index: 7943980 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4528. Min Range: -5.4528
Max Act: 4.7653. Min Act: -0.1700
Data Index: 6277597 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4528. Min Range: -5.4528
Max Act: 4.7653. Min Act: -0.1700
Data Index: 388931 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4528. Min Range: -5.4528
Max Act: 4.7653. Min Act: -0.1700
Data Index: 5144967 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4528. Min Range: -5.4528
Max Act: 4.7653. Min Act: -0.1700
Data Index: 6263278 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4528. Min Range: -5.4528
Max Act: 4.7653. Min Act: -0.1700
Data Index: 3697157 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4528. Min Range: -5.4528
Max Act: 4.7653. Min Act: -0.1700
Data Index: 8434703 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19