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

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

Neuron 2064 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7520. Min Act: -0.0000

Data Index: 283720 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.8433. Min Act: -0.0000

Data Index: 922223 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7307. Min Act: -0.0000

Data Index: 1450488 (Python Code)

Max Activating Token Index: 206

Text #3

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7884. Min Act: -0.0000

Data Index: 435519 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7959. Min Act: -0.0000

Data Index: 534395 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.5852. Min Act: -0.0000

Data Index: 443070 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.6601. Min Act: -0.0000

Data Index: 1221522 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.7366. Min Act: -0.0000

Data Index: 780583 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.5348. Min Act: -0.0000

Data Index: 767132 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.5013. Min Act: -0.0000

Data Index: 341219 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.5928. Min Act: -0.0000

Data Index: 1136686 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.4709. Min Act: -0.0000

Data Index: 1325921 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.4378. Min Act: -0.0000

Data Index: 1638263 (Python Code)

Max Activating Token Index: 386

Text #13

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.3765. Min Act: -0.0000

Data Index: 46339 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.4456. Min Act: -0.0000

Data Index: 772367 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.2634. Min Act: -0.0000

Data Index: 28148 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.3440. Min Act: -0.0000

Data Index: 1515981 (Python Code)

Max Activating Token Index: 315

Text #17

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.3765. Min Act: -0.0000

Data Index: 1118537 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.3932. Min Act: -0.0000

Data Index: 1584231 (Python Code)

Max Activating Token Index: 76

Text #19

Max Range: 1.8433. Min Range: -1.8433

Max Act: 1.3549. Min Act: -0.0000

Data Index: 1386059 (Python Code)

Max Activating Token Index: 367