Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 6015 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5601. Min Range: -2.5601

Max Act: 2.5601. Min Act: -0.0000

Data Index: 1271525 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 2.5601. Min Range: -2.5601

Max Act: 2.5140. Min Act: -0.0000

Data Index: 791216 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 2.5601. Min Range: -2.5601

Max Act: 2.2099. Min Act: -0.0000

Data Index: 402595 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 2.5601. Min Range: -2.5601

Max Act: 2.2335. Min Act: -0.0000

Data Index: 821433 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 2.5601. Min Range: -2.5601

Max Act: 2.1157. Min Act: -0.0000

Data Index: 221653 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 2.5601. Min Range: -2.5601

Max Act: 2.1826. Min Act: -0.0000

Data Index: 600592 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 2.5601. Min Range: -2.5601

Max Act: 2.0897. Min Act: -0.0000

Data Index: 713195 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 2.5601. Min Range: -2.5601

Max Act: 2.0792. Min Act: -0.0000

Data Index: 72557 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 2.5601. Min Range: -2.5601

Max Act: 2.0749. Min Act: -0.0000

Data Index: 234914 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 2.5601. Min Range: -2.5601

Max Act: 2.0581. Min Act: -0.0000

Data Index: 539450 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 2.5601. Min Range: -2.5601

Max Act: 2.0261. Min Act: -0.0000

Data Index: 529056 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 2.5601. Min Range: -2.5601

Max Act: 1.9889. Min Act: -0.0000

Data Index: 696014 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 2.5601. Min Range: -2.5601

Max Act: 1.9481. Min Act: -0.0000

Data Index: 922582 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 2.5601. Min Range: -2.5601

Max Act: 1.9418. Min Act: -0.0000

Data Index: 1189760 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 2.5601. Min Range: -2.5601

Max Act: 1.9237. Min Act: -0.0000

Data Index: 1349444 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 2.5601. Min Range: -2.5601

Max Act: 1.9766. Min Act: -0.0000

Data Index: 342405 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 2.5601. Min Range: -2.5601

Max Act: 1.8593. Min Act: -0.0000

Data Index: 1085492 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 2.5601. Min Range: -2.5601

Max Act: 1.9504. Min Act: -0.0000

Data Index: 345836 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 2.5601. Min Range: -2.5601

Max Act: 1.9437. Min Act: -0.0000

Data Index: 656111 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 2.5601. Min Range: -2.5601

Max Act: 1.8332. Min Act: -0.0000

Data Index: 1260954 (C4 (Web Text))

Max Activating Token Index: 622