Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1712 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3716. Min Range: -7.3716
Max Act: 7.3716. Min Act: -0.1700
Data Index: 7109139 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3716. Min Range: -7.3716
Max Act: 7.1841. Min Act: -0.1700
Data Index: 4835276 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3716. Min Range: -7.3716
Max Act: 7.1528. Min Act: -0.1700
Data Index: 8615439 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.8403. Min Act: -0.1700
Data Index: 3743017 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.8091. Min Act: -0.1700
Data Index: 7074775 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.7153. Min Act: -0.1700
Data Index: 3227824 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.7153. Min Act: -0.1700
Data Index: 8615440 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.7466. Min Act: -0.1700
Data Index: 712358 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.6528. Min Act: -0.1700
Data Index: 622665 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.6528. Min Act: -0.1700
Data Index: 120075 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.6216. Min Act: -0.1700
Data Index: 3990534 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.6216. Min Act: -0.1700
Data Index: 4621557 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.4966. Min Act: -0.1700
Data Index: 6279522 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.5591. Min Act: -0.1700
Data Index: 6865101 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.5591. Min Act: -0.1700
Data Index: 5980131 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.5903. Min Act: -0.1700
Data Index: 7272138 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.5278. Min Act: -0.1700
Data Index: 7670835 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.4966. Min Act: -0.1700
Data Index: 954287 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.4966. Min Act: -0.1700
Data Index: 7416238 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3716. Min Range: -7.3716
Max Act: 6.4653. Min Act: -0.1700
Data Index: 5638735 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19