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

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

Neuron 632 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1250445 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0513. Min Act: -0.0002

Data Index: 429628 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0410. Min Act: -0.0002

Data Index: 631844 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0384. Min Act: -0.0002

Data Index: 802817 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1352890 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0353. Min Act: -0.0002

Data Index: 536677 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1219080 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0369. Min Act: -0.0002

Data Index: 365068 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0339. Min Act: -0.0002

Data Index: 323034 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0334. Min Act: -0.0002

Data Index: 507925 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0340. Min Act: -0.0002

Data Index: 977001 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1020703 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0335. Min Act: -0.0002

Data Index: 450300 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1107800 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0327. Min Act: -0.0002

Data Index: 866143 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1187366 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0312. Min Act: -0.0002

Data Index: 907412 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0329. Min Act: -0.0002

Data Index: 29018 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0308. Min Act: -0.0002

Data Index: 145249 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0307. Min Act: -0.0002

Data Index: 650669 (C4 (Web Text))

Max Activating Token Index: 445