Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 900 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.9551. Min Act: -0.1700
Data Index: 785160 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.9551. Min Act: -0.1700
Data Index: 2458307 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.8613. Min Act: -0.1700
Data Index: 4504826 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7988. Min Act: -0.1700
Data Index: 4429446 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7676. Min Act: -0.1700
Data Index: 2285215 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.8301. Min Act: -0.1700
Data Index: 64945 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7676. Min Act: -0.1700
Data Index: 1083933 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7676. Min Act: -0.1700
Data Index: 6125888 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7676. Min Act: -0.1700
Data Index: 1377494 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7676. Min Act: -0.1700
Data Index: 8034391 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7363. Min Act: -0.1700
Data Index: 5270524 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7363. Min Act: -0.1700
Data Index: 5844227 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7051. Min Act: -0.1700
Data Index: 8565986 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7363. Min Act: -0.1700
Data Index: 1150750 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7676. Min Act: -0.1700
Data Index: 7461729 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7051. Min Act: -0.1700
Data Index: 6728549 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.6738. Min Act: -0.1700
Data Index: 6456495 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7051. Min Act: -0.1700
Data Index: 5969332 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7051. Min Act: -0.1700
Data Index: 5839518 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.6738. Min Act: -0.1700
Data Index: 8594383 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19