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

Dataset: The Pile

Neuron 4616 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: 0.4350. Min Range: -0.4350

Max Act: 0.4350. Min Act: -0.0000

Data Index: 393269 (The Pile)

Max Activating Token Index: 189

Text #1

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.4252. Min Act: -0.0000

Data Index: 341495 (The Pile)

Max Activating Token Index: 474

Text #2

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1570967 (The Pile)

Max Activating Token Index: 485

Text #3

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3482. Min Act: -0.0000

Data Index: 183790 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3550. Min Act: -0.0000

Data Index: 591420 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3519. Min Act: -0.0000

Data Index: 726596 (The Pile)

Max Activating Token Index: 517

Text #6

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3383. Min Act: -0.0000

Data Index: 519784 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1939327 (The Pile)

Max Activating Token Index: 594

Text #8

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1863752 (The Pile)

Max Activating Token Index: 170

Text #9

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1459392 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3443. Min Act: -0.0000

Data Index: 995877 (The Pile)

Max Activating Token Index: 896

Text #11

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3728. Min Act: -0.0000

Data Index: 991649 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1426746 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3026. Min Act: -0.0000

Data Index: 158729 (The Pile)

Max Activating Token Index: 473

Text #14

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1380448 (The Pile)

Max Activating Token Index: 725

Text #15

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1526244 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1712998 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1395774 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1945523 (The Pile)

Max Activating Token Index: 249

Text #19

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1766269 (The Pile)

Max Activating Token Index: 1005