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

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

Neuron 1336 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2320. Min Range: -3.2320

Max Act: 3.2320. Min Act: -0.0000

Data Index: 299920 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.7524. Min Act: -0.0000

Data Index: 1102881 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.6308. Min Act: -0.0000

Data Index: 23328 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.6275. Min Act: -0.0000

Data Index: 315396 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.4616. Min Act: -0.0000

Data Index: 918643 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.2162. Min Act: -0.0000

Data Index: 1106762 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.0914. Min Act: -0.0000

Data Index: 533076 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.1079. Min Act: -0.0000

Data Index: 1057651 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.2113. Min Act: -0.0000

Data Index: 55811 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.0249. Min Act: -0.0000

Data Index: 447542 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.0729. Min Act: -0.0000

Data Index: 367562 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.0419. Min Act: -0.0000

Data Index: 1126921 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.0340. Min Act: -0.0000

Data Index: 250299 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 3.2320. Min Range: -3.2320

Max Act: 1.9240. Min Act: -0.0000

Data Index: 711476 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 3.2320. Min Range: -3.2320

Max Act: 2.0542. Min Act: -0.0000

Data Index: 1095870 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 3.2320. Min Range: -3.2320

Max Act: 1.8762. Min Act: -0.0000

Data Index: 402478 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 3.2320. Min Range: -3.2320

Max Act: 1.7309. Min Act: -0.0000

Data Index: 974145 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 3.2320. Min Range: -3.2320

Max Act: 1.7976. Min Act: -0.0000

Data Index: 846053 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 3.2320. Min Range: -3.2320

Max Act: 1.7738. Min Act: -0.0000

Data Index: 573882 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 3.2320. Min Range: -3.2320

Max Act: 1.7587. Min Act: -0.0000

Data Index: 1160175 (C4 (Web Text))

Max Activating Token Index: 950