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

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

Neuron 4938 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: 0.0431. Min Range: -0.0431

Max Act: 0.0431. Min Act: -0.0003

Data Index: 706028 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0402. Min Act: -0.0002

Data Index: 967333 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0367. Min Act: -0.0003

Data Index: 344545 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0393. Min Act: -0.0003

Data Index: 177481 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1580065 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1137527 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0359. Min Act: -0.0002

Data Index: 375423 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1446287 (Python Code)

Max Activating Token Index: 222

Text #8

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0359. Min Act: -0.0003

Data Index: 16118 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0342. Min Act: -0.0003

Data Index: 65857 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0341. Min Act: -0.0002

Data Index: 207296 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1603402 (Python Code)

Max Activating Token Index: 364

Text #12

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0340. Min Act: -0.0002

Data Index: 328046 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0336. Min Act: -0.0002

Data Index: 839958 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1549149 (Python Code)

Max Activating Token Index: 742

Text #15

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1502777 (Python Code)

Max Activating Token Index: 796

Text #16

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0358. Min Act: -0.0002

Data Index: 29679 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0307. Min Act: -0.0002

Data Index: 510275 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1048049 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1581681 (Python Code)

Max Activating Token Index: 277