Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1180 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0605. Min Act: -0.0003

Data Index: 324148 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0568. Min Act: -0.0003

Data Index: 648832 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0509. Min Act: -0.0004

Data Index: 669656 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1329097 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0469. Min Act: -0.0003

Data Index: 461461 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0463. Min Act: -0.0004

Data Index: 528539 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0454. Min Act: -0.0003

Data Index: 11864 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0427. Min Act: -0.0003

Data Index: 125271 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0388. Min Act: -0.0004

Data Index: 268795 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0409. Min Act: -0.0004

Data Index: 240442 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1136864 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0414. Min Act: -0.0003

Data Index: 942528 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1275414 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1259586 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0392. Min Act: -0.0003

Data Index: 905209 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0376. Min Act: -0.0003

Data Index: 477767 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0372. Min Act: -0.0003

Data Index: 926692 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0380. Min Act: -0.0003

Data Index: 767938 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0360. Min Act: -0.0003

Data Index: 180549 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0370. Min Act: -0.0003

Data Index: 159359 (C4 (Web Text))

Max Activating Token Index: 548