Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1735 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1425. Min Act: -0.0003

Data Index: 982303 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1479. Min Act: -0.0003

Data Index: 275260 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1748. Min Act: -0.0003

Data Index: 64404 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1137. Min Act: -0.0003

Data Index: 1037701 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0785. Min Act: -0.0003

Data Index: 256758 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1020. Min Act: -0.0003

Data Index: 496199 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0181. Min Act: -0.0003

Data Index: 32651 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0748. Min Act: -0.0003

Data Index: 1280260 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0411. Min Act: -0.0003

Data Index: 292532 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0514. Min Act: -0.0003

Data Index: 281574 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0732. Min Act: -0.0003

Data Index: 1019538 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0411. Min Act: -0.0003

Data Index: 231760 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1086. Min Act: -0.0003

Data Index: 64122 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1381. Min Act: -0.0003

Data Index: 956841 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0651. Min Act: -0.0003

Data Index: 1219727 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9933. Min Act: -0.0003

Data Index: 1245326 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9356. Min Act: -0.0003

Data Index: 558354 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0226. Min Act: -0.0003

Data Index: 1103973 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9577. Min Act: -0.0003

Data Index: 421861 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1060. Min Act: -0.0003

Data Index: 1023801 (C4 (Web Text))

Max Activating Token Index: 430