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

Dataset: The Pile

Neuron 3670 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: 0.3709. Min Range: -0.3709

Max Act: 0.3597. Min Act: -0.0000

Data Index: 842471 (The Pile)

Max Activating Token Index: 657

Text #1

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3709. Min Act: -0.0000

Data Index: 519670 (The Pile)

Max Activating Token Index: 559

Text #2

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1511939 (The Pile)

Max Activating Token Index: 104

Text #3

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1674873 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3083. Min Act: -0.0000

Data Index: 970407 (The Pile)

Max Activating Token Index: 995

Text #5

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1911147 (The Pile)

Max Activating Token Index: 546

Text #6

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3319. Min Act: -0.0000

Data Index: 647530 (The Pile)

Max Activating Token Index: 980

Text #7

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2924. Min Act: -0.0000

Data Index: 207476 (The Pile)

Max Activating Token Index: 950

Text #8

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2628. Min Act: -0.0000

Data Index: 8240 (The Pile)

Max Activating Token Index: 711

Text #9

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2563. Min Act: -0.0000

Data Index: 501773 (The Pile)

Max Activating Token Index: 602

Text #10

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2408. Min Act: -0.0000

Data Index: 525230 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2374. Min Act: -0.0000

Data Index: 220998 (The Pile)

Max Activating Token Index: 763

Text #12

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1256013 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2398. Min Act: -0.0000

Data Index: 572246 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1232702 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2384. Min Act: -0.0000

Data Index: 401234 (The Pile)

Max Activating Token Index: 813

Text #16

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2237. Min Act: -0.0000

Data Index: 332337 (The Pile)

Max Activating Token Index: 230

Text #17

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1520111 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2134. Min Act: -0.0000

Data Index: 914447 (The Pile)

Max Activating Token Index: 317

Text #19

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1628551 (The Pile)

Max Activating Token Index: 773