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

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

Neuron 535 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: 5.7538. Min Range: -5.7538

Max Act: 5.7538. Min Act: -0.0000

Data Index: 78007 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 5.7538. Min Range: -5.7538

Max Act: 5.0314. Min Act: -0.0000

Data Index: 553909 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 5.7538. Min Range: -5.7538

Max Act: 4.8069. Min Act: -0.0000

Data Index: 21387 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 5.7538. Min Range: -5.7538

Max Act: 4.3551. Min Act: -0.0000

Data Index: 311934 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 5.7538. Min Range: -5.7538

Max Act: 4.6271. Min Act: -0.0000

Data Index: 624637 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 5.7538. Min Range: -5.7538

Max Act: 4.2479. Min Act: -0.0000

Data Index: 129978 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 5.7538. Min Range: -5.7538

Max Act: 4.3331. Min Act: -0.0000

Data Index: 40437 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 5.7538. Min Range: -5.7538

Max Act: 4.1072. Min Act: -0.0000

Data Index: 516444 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 5.7538. Min Range: -5.7538

Max Act: 3.6667. Min Act: -0.0000

Data Index: 1156205 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 5.7538. Min Range: -5.7538

Max Act: 3.6139. Min Act: -0.0000

Data Index: 965517 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 5.7538. Min Range: -5.7538

Max Act: 3.4412. Min Act: -0.0000

Data Index: 502205 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 5.7538. Min Range: -5.7538

Max Act: 3.6605. Min Act: -0.0000

Data Index: 820039 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 5.7538. Min Range: -5.7538

Max Act: 3.4433. Min Act: -0.0000

Data Index: 1047817 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 5.7538. Min Range: -5.7538

Max Act: 3.3252. Min Act: -0.0000

Data Index: 409795 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 5.7538. Min Range: -5.7538

Max Act: 3.5559. Min Act: -0.0000

Data Index: 493745 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 5.7538. Min Range: -5.7538

Max Act: 3.0145. Min Act: -0.0000

Data Index: 297335 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 5.7538. Min Range: -5.7538

Max Act: 2.9440. Min Act: -0.0000

Data Index: 1143765 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 5.7538. Min Range: -5.7538

Max Act: 2.9871. Min Act: -0.0000

Data Index: 1254381 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 5.7538. Min Range: -5.7538

Max Act: 2.7852. Min Act: -0.0000

Data Index: 203438 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 5.7538. Min Range: -5.7538

Max Act: 2.7758. Min Act: -0.0000

Data Index: 43724 (C4 (Web Text))

Max Activating Token Index: 94