Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4002 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1031365 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1658765 (The Pile)

Max Activating Token Index: 399

Text #2

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1219141 (The Pile)

Max Activating Token Index: 273

Text #3

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1094142 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1485296 (The Pile)

Max Activating Token Index: 416

Text #5

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2409. Min Act: -0.0000

Data Index: 717535 (The Pile)

Max Activating Token Index: 491

Text #6

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2613. Min Act: -0.0000

Data Index: 561484 (The Pile)

Max Activating Token Index: 349

Text #7

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1620426 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2508. Min Act: -0.0000

Data Index: 1462145 (The Pile)

Max Activating Token Index: 672

Text #9

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2331. Min Act: -0.0000

Data Index: 747710 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2464. Min Act: -0.0000

Data Index: 452041 (The Pile)

Max Activating Token Index: 822

Text #11

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1515619 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1894514 (The Pile)

Max Activating Token Index: 616

Text #13

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1151010 (The Pile)

Max Activating Token Index: 574

Text #14

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1220557 (The Pile)

Max Activating Token Index: 694

Text #15

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2337. Min Act: -0.0000

Data Index: 166096 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1446029 (The Pile)

Max Activating Token Index: 823

Text #17

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1513037 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2240. Min Act: -0.0000

Data Index: 878602 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1312660 (The Pile)

Max Activating Token Index: 422