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

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

Neuron 5086 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1157851 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3800. Min Act: -0.0000

Data Index: 761487 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3763. Min Act: -0.0000

Data Index: 823987 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3289. Min Act: -0.0000

Data Index: 1164913 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3348. Min Act: -0.0000

Data Index: 611124 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2986. Min Act: -0.0000

Data Index: 794858 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1115755 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1344658 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2648. Min Act: -0.0000

Data Index: 247257 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1183522 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2486. Min Act: -0.0000

Data Index: 691402 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2498. Min Act: 0.0000

Data Index: 1191016 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2394. Min Act: -0.0000

Data Index: 512038 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2573. Min Act: -0.0000

Data Index: 41382 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2476. Min Act: -0.0000

Data Index: 940268 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1016029 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1229046 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2275. Min Act: -0.0000

Data Index: 192267 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2360. Min Act: -0.0000

Data Index: 473097 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.2286. Min Act: -0.0000

Data Index: 488394 (C4 (Web Text))

Max Activating Token Index: 76