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

Dataset: The Pile

Neuron 4425 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0000

Data Index: 832459 (The Pile)

Max Activating Token Index: 653

Text #1

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0360. Min Act: -0.0000

Data Index: 723869 (The Pile)

Max Activating Token Index: 416

Text #2

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0331. Min Act: -0.0000

Data Index: 562219 (The Pile)

Max Activating Token Index: 534

Text #3

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0321. Min Act: -0.0000

Data Index: 5822 (The Pile)

Max Activating Token Index: 651

Text #4

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0327. Min Act: -0.0000

Data Index: 1590884 (The Pile)

Max Activating Token Index: 213

Text #5

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1494938 (The Pile)

Max Activating Token Index: 408

Text #6

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0338. Min Act: -0.0000

Data Index: 132680 (The Pile)

Max Activating Token Index: 359

Text #7

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0322. Min Act: -0.0000

Data Index: 1331479 (The Pile)

Max Activating Token Index: 555

Text #8

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0322. Min Act: -0.0000

Data Index: 1230192 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1986298 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0287. Min Act: -0.0000

Data Index: 751817 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0330. Min Act: -0.0000

Data Index: 1255106 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0334. Min Act: -0.0000

Data Index: 1860082 (The Pile)

Max Activating Token Index: 411

Text #13

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0272. Min Act: -0.0000

Data Index: 1327632 (The Pile)

Max Activating Token Index: 659

Text #14

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0303. Min Act: -0.0000

Data Index: 508969 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0314. Min Act: -0.0000

Data Index: 939135 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1323166 (The Pile)

Max Activating Token Index: 361

Text #17

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0309. Min Act: -0.0000

Data Index: 1610306 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0315. Min Act: -0.0000

Data Index: 703366 (The Pile)

Max Activating Token Index: 930

Text #19

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0318. Min Act: -0.0000

Data Index: 15662 (The Pile)

Max Activating Token Index: 597