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

Dataset: The Pile

Neuron 1433 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2956. Min Act: 0.0000

Data Index: 144592 (The Pile)

Max Activating Token Index: 387

Text #1

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2997. Min Act: -0.0000

Data Index: 836342 (The Pile)

Max Activating Token Index: 468

Text #2

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2923. Min Act: -0.0000

Data Index: 669075 (The Pile)

Max Activating Token Index: 83

Text #3

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2780. Min Act: -0.0000

Data Index: 64975 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2527. Min Act: 0.0000

Data Index: 802418 (The Pile)

Max Activating Token Index: 639

Text #5

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1764340 (The Pile)

Max Activating Token Index: 855

Text #6

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1570630 (The Pile)

Max Activating Token Index: 998

Text #7

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2458. Min Act: -0.0000

Data Index: 477262 (The Pile)

Max Activating Token Index: 84

Text #8

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2435. Min Act: -0.0000

Data Index: 511635 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2391. Min Act: -0.0000

Data Index: 868659 (The Pile)

Max Activating Token Index: 218

Text #10

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2369. Min Act: -0.0000

Data Index: 459388 (The Pile)

Max Activating Token Index: 814

Text #11

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1076461 (The Pile)

Max Activating Token Index: 204

Text #12

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1031366 (The Pile)

Max Activating Token Index: 88

Text #13

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2241. Min Act: -0.0000

Data Index: 539765 (The Pile)

Max Activating Token Index: 592

Text #14

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2276. Min Act: -0.0000

Data Index: 1571836 (The Pile)

Max Activating Token Index: 726

Text #15

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2314. Min Act: -0.0000

Data Index: 754011 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1221478 (The Pile)

Max Activating Token Index: 584

Text #17

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2357. Min Act: 0.0000

Data Index: 1040789 (The Pile)

Max Activating Token Index: 693

Text #18

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2269. Min Act: -0.0000

Data Index: 930236 (The Pile)

Max Activating Token Index: 873

Text #19

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1101487 (The Pile)

Max Activating Token Index: 514