Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1919 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3085. Min Range: -6.3085
Max Act: 6.3085. Min Act: -0.1700
Data Index: 6451137 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.9647. Min Act: -0.1700
Data Index: 4147598 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.8710. Min Act: -0.1700
Data Index: 5280830 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.8085. Min Act: -0.1700
Data Index: 6582335 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.7772. Min Act: -0.1700
Data Index: 190840 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.7460. Min Act: -0.1700
Data Index: 1816938 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.7772. Min Act: -0.1700
Data Index: 1914794 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.7460. Min Act: -0.1700
Data Index: 1443567 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.7460. Min Act: -0.1700
Data Index: 1772376 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.7460. Min Act: -0.1700
Data Index: 6582336 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.7147. Min Act: -0.1700
Data Index: 2837826 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.7147. Min Act: -0.1700
Data Index: 5631464 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.7147. Min Act: -0.1700
Data Index: 2803462 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.6835. Min Act: -0.1700
Data Index: 6713540 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.6522. Min Act: -0.1700
Data Index: 5579168 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.6835. Min Act: -0.1700
Data Index: 5528218 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.6522. Min Act: -0.1700
Data Index: 3531372 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.6835. Min Act: -0.1700
Data Index: 8693082 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.5897. Min Act: -0.1700
Data Index: 950791 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3085. Min Range: -6.3085
Max Act: 5.6522. Min Act: -0.1700
Data Index: 1683848 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19