Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2074 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0583. Min Act: -0.0002

Data Index: 549408 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0546. Min Act: -0.0002

Data Index: 707661 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0468. Min Act: -0.0002

Data Index: 266888 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1060978 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0461. Min Act: -0.0002

Data Index: 284040 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0459. Min Act: -0.0002

Data Index: 380982 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0480. Min Act: -0.0002

Data Index: 914778 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0504. Min Act: -0.0002

Data Index: 544549 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0475. Min Act: -0.0002

Data Index: 383967 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0484. Min Act: -0.0002

Data Index: 353900 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0435. Min Act: -0.0002

Data Index: 559957 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0446. Min Act: -0.0002

Data Index: 516004 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1323228 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0395. Min Act: -0.0002

Data Index: 95114 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1292040 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0449. Min Act: -0.0002

Data Index: 633897 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0428. Min Act: -0.0002

Data Index: 895042 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1017170 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1332659 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1333386 (C4 (Web Text))

Max Activating Token Index: 136