Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1978 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0380. Min Act: -0.0002

Data Index: 178190 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0365. Min Act: -0.0002

Data Index: 296158 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0362. Min Act: -0.0002

Data Index: 660848 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0357. Min Act: -0.0002

Data Index: 36097 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1272846 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1209754 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1250811 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1333307 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0336. Min Act: -0.0002

Data Index: 803052 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0328. Min Act: -0.0002

Data Index: 597944 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1072874 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0327. Min Act: -0.0002

Data Index: 96677 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0326. Min Act: -0.0002

Data Index: 959850 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0325. Min Act: -0.0002

Data Index: 203790 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1223791 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1003944 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0320. Min Act: -0.0002

Data Index: 327615 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0322. Min Act: -0.0002

Data Index: 254082 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0312. Min Act: -0.0002

Data Index: 918508 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0311. Min Act: -0.0002

Data Index: 51317 (C4 (Web Text))

Max Activating Token Index: 450