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

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

Neuron 1440 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0383. Min Act: -0.0005

Data Index: 172628 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0340. Min Act: -0.0006

Data Index: 522983 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0341. Min Act: -0.0006

Data Index: 497106 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0347. Min Act: -0.0006

Data Index: 918476 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0332. Min Act: -0.0006

Data Index: 392201 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0322. Min Act: -0.0006

Data Index: 1160744 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0340. Min Act: -0.0006

Data Index: 1356549 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0340. Min Act: -0.0006

Data Index: 1250716 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0305. Min Act: -0.0006

Data Index: 827017 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0321. Min Act: -0.0006

Data Index: 590140 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0328. Min Act: -0.0006

Data Index: 296914 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0341. Min Act: -0.0006

Data Index: 190333 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0319. Min Act: -0.0006

Data Index: 647070 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0311. Min Act: -0.0006

Data Index: 789108 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0332. Min Act: -0.0006

Data Index: 1279628 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0310. Min Act: -0.0006

Data Index: 267479 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0314. Min Act: -0.0006

Data Index: 546683 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0295. Min Act: -0.0006

Data Index: 751835 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0313. Min Act: -0.0006

Data Index: 851348 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0314. Min Act: -0.0006

Data Index: 929333 (C4 (Web Text))

Max Activating Token Index: 346