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

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

Neuron 5974 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.7324. Min Act: 0.0000

Data Index: 876103 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.4570. Min Act: -0.0000

Data Index: 372424 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.4481. Min Act: 0.0000

Data Index: 1342590 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.2984. Min Act: 0.0000

Data Index: 120915 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.2961. Min Act: -0.0000

Data Index: 829833 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.1395. Min Act: -0.0000

Data Index: 1016883 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.2117. Min Act: 0.0000

Data Index: 159174 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.2729. Min Act: -0.0000

Data Index: 1065387 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.1652. Min Act: -0.0000

Data Index: 911903 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.0837. Min Act: -0.0000

Data Index: 765173 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.1322. Min Act: -0.0000

Data Index: 479645 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.0539. Min Act: -0.0000

Data Index: 83099 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 1.7324. Min Range: -1.7324

Max Act: 0.9796. Min Act: -0.0000

Data Index: 136005 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.0938. Min Act: -0.0000

Data Index: 364639 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.0896. Min Act: -0.0000

Data Index: 967743 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.0543. Min Act: -0.0000

Data Index: 442608 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.0366. Min Act: -0.0000

Data Index: 373036 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.0669. Min Act: -0.0000

Data Index: 352290 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.0789. Min Act: 0.0001

Data Index: 511438 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.0166. Min Act: 0.0000

Data Index: 971016 (C4 (Web Text))

Max Activating Token Index: 668