Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4925 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9195. Min Range: -7.9195
Max Act: 7.9195. Min Act: -0.1700
Data Index: 6276654 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9195. Min Range: -7.9195
Max Act: 7.7320. Min Act: -0.1700
Data Index: 1570583 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9195. Min Range: -7.9195
Max Act: 7.4195. Min Act: -0.1700
Data Index: 5164811 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9195. Min Range: -7.9195
Max Act: 7.2945. Min Act: -0.1700
Data Index: 5858269 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9195. Min Range: -7.9195
Max Act: 7.2320. Min Act: -0.1700
Data Index: 5886667 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9195. Min Range: -7.9195
Max Act: 7.1383. Min Act: -0.1700
Data Index: 5174441 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9195. Min Range: -7.9195
Max Act: 7.0758. Min Act: -0.1700
Data Index: 7611244 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9195. Min Range: -7.9195
Max Act: 7.0133. Min Act: -0.1700
Data Index: 7119686 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9195. Min Range: -7.9195
Max Act: 7.0133. Min Act: -0.1700
Data Index: 1603491 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9195. Min Range: -7.9195
Max Act: 7.0133. Min Act: -0.1700
Data Index: 7416431 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9195. Min Range: -7.9195
Max Act: 6.9508. Min Act: -0.1700
Data Index: 2471816 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9195. Min Range: -7.9195
Max Act: 6.9195. Min Act: -0.1700
Data Index: 3109768 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9195. Min Range: -7.9195
Max Act: 6.8570. Min Act: -0.1700
Data Index: 571765 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9195. Min Range: -7.9195
Max Act: 6.8570. Min Act: -0.1700
Data Index: 1886285 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9195. Min Range: -7.9195
Max Act: 6.7945. Min Act: -0.1700
Data Index: 639423 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9195. Min Range: -7.9195
Max Act: 6.7945. Min Act: -0.1700
Data Index: 5174442 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9195. Min Range: -7.9195
Max Act: 6.7945. Min Act: -0.1700
Data Index: 7646587 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9195. Min Range: -7.9195
Max Act: 6.7633. Min Act: -0.1700
Data Index: 7160706 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9195. Min Range: -7.9195
Max Act: 6.7320. Min Act: -0.1700
Data Index: 1652577 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9195. Min Range: -7.9195
Max Act: 6.7008. Min Act: -0.1700
Data Index: 5510672 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19