Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3942 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.8000. Min Act: -0.1700
Data Index: 7668545 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.8000. Min Act: -0.1700
Data Index: 8607360 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.8000. Min Act: -0.1700
Data Index: 4078970 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.6125. Min Act: -0.1700
Data Index: 7247594 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.5812. Min Act: -0.1700
Data Index: 3884633 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.5500. Min Act: -0.1700
Data Index: 619845 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.5500. Min Act: -0.1700
Data Index: 6597647 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.5187. Min Act: -0.1700
Data Index: 3464808 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.5187. Min Act: -0.1700
Data Index: 92055 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.5187. Min Act: -0.1700
Data Index: 6137312 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.5187. Min Act: -0.1700
Data Index: 4095157 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.5500. Min Act: -0.1700
Data Index: 2780269 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.5187. Min Act: -0.1700
Data Index: 3009262 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.4875. Min Act: -0.1700
Data Index: 7689866 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.4875. Min Act: -0.1700
Data Index: 8546 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.4562. Min Act: -0.1700
Data Index: 2442709 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.4250. Min Act: -0.1700
Data Index: 7028693 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.4562. Min Act: -0.1700
Data Index: 2150772 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.4250. Min Act: -0.1700
Data Index: 6650026 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8000. Min Range: -5.8000
Max Act: 5.4250. Min Act: -0.1700
Data Index: 2508808 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19