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

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

Neuron 3897 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1186. Min Range: -4.1186

Max Act: 4.1186. Min Act: -0.0000

Data Index: 264649 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 4.1186. Min Range: -4.1186

Max Act: 3.2960. Min Act: 0.0000

Data Index: 1219384 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 4.1186. Min Range: -4.1186

Max Act: 2.7117. Min Act: -0.0000

Data Index: 763728 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 4.1186. Min Range: -4.1186

Max Act: 2.6397. Min Act: 0.0000

Data Index: 1228547 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 4.1186. Min Range: -4.1186

Max Act: 2.6919. Min Act: -0.0000

Data Index: 927326 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 4.1186. Min Range: -4.1186

Max Act: 2.4351. Min Act: -0.0000

Data Index: 328612 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 4.1186. Min Range: -4.1186

Max Act: 2.3571. Min Act: -0.0000

Data Index: 447645 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 4.1186. Min Range: -4.1186

Max Act: 2.3028. Min Act: -0.0000

Data Index: 1294542 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 4.1186. Min Range: -4.1186

Max Act: 2.2765. Min Act: -0.0000

Data Index: 338933 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 4.1186. Min Range: -4.1186

Max Act: 2.2181. Min Act: -0.0000

Data Index: 638974 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 4.1186. Min Range: -4.1186

Max Act: 2.2825. Min Act: -0.0000

Data Index: 138952 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 4.1186. Min Range: -4.1186

Max Act: 2.2525. Min Act: -0.0000

Data Index: 358616 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 4.1186. Min Range: -4.1186

Max Act: 2.0598. Min Act: 0.0000

Data Index: 972335 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 4.1186. Min Range: -4.1186

Max Act: 1.9606. Min Act: -0.0000

Data Index: 198188 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 4.1186. Min Range: -4.1186

Max Act: 1.9559. Min Act: -0.0000

Data Index: 1163583 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 4.1186. Min Range: -4.1186

Max Act: 1.9558. Min Act: -0.0000

Data Index: 1223331 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 4.1186. Min Range: -4.1186

Max Act: 1.9371. Min Act: -0.0000

Data Index: 1162793 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 4.1186. Min Range: -4.1186

Max Act: 1.9369. Min Act: -0.0000

Data Index: 328131 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 4.1186. Min Range: -4.1186

Max Act: 1.8802. Min Act: 0.0000

Data Index: 911982 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 4.1186. Min Range: -4.1186

Max Act: 1.7725. Min Act: 0.0000

Data Index: 1120214 (C4 (Web Text))

Max Activating Token Index: 905