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

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

Neuron 172 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: 0.9308. Min Range: -0.9308

Max Act: 0.8926. Min Act: -0.0000

Data Index: 118002 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.8922. Min Act: -0.0000

Data Index: 674157 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1100890 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7897. Min Act: -0.0000

Data Index: 264320 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.8301. Min Act: -0.0000

Data Index: 726771 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.8102. Min Act: -0.0000

Data Index: 479212 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1327388 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7947. Min Act: -0.0000

Data Index: 53881 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.8163. Min Act: -0.0000

Data Index: 489238 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1289450 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.8697. Min Act: -0.0000

Data Index: 389581 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7406. Min Act: -0.0000

Data Index: 320947 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7353. Min Act: -0.0000

Data Index: 152680 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6732. Min Act: -0.0000

Data Index: 756335 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7360. Min Act: -0.0000

Data Index: 668326 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1338815 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7535. Min Act: -0.0000

Data Index: 928624 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7657. Min Act: -0.0000

Data Index: 21779 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7159. Min Act: -0.0000

Data Index: 981574 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6833. Min Act: -0.0000

Data Index: 35594 (C4 (Web Text))

Max Activating Token Index: 352