Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 103 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0381. Min Act: -0.0006

Data Index: 835930 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0373. Min Act: -0.0006

Data Index: 858640 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0352. Min Act: -0.0006

Data Index: 131286 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0354. Min Act: -0.0006

Data Index: 93163 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0352. Min Act: -0.0006

Data Index: 308723 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0343. Min Act: -0.0006

Data Index: 83001 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0348. Min Act: -0.0006

Data Index: 165519 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0347. Min Act: -0.0006

Data Index: 255513 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0337. Min Act: -0.0006

Data Index: 134290 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0313. Min Act: -0.0006

Data Index: 507487 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0327. Min Act: -0.0006

Data Index: 1044212 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0317. Min Act: -0.0006

Data Index: 672208 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0311. Min Act: -0.0006

Data Index: 1020522 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0317. Min Act: -0.0006

Data Index: 766218 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0306. Min Act: -0.0006

Data Index: 243194 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0310. Min Act: -0.0006

Data Index: 17294 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0311. Min Act: -0.0006

Data Index: 1176618 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0318. Min Act: -0.0006

Data Index: 643371 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0312. Min Act: -0.0006

Data Index: 297959 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0304. Min Act: -0.0006

Data Index: 751242 (C4 (Web Text))

Max Activating Token Index: 373