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

Dataset: The Pile

Neuron 1548 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: 0.3298. Min Range: -0.3298

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1846523 (The Pile)

Max Activating Token Index: 86

Text #1

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1905558 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2844. Min Act: -0.0000

Data Index: 248495 (The Pile)

Max Activating Token Index: 320

Text #3

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.3111. Min Act: -0.0000

Data Index: 155025 (The Pile)

Max Activating Token Index: 424

Text #4

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2722. Min Act: -0.0000

Data Index: 1069579 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2574. Min Act: -0.0000

Data Index: 945245 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2829. Min Act: -0.0000

Data Index: 1418728 (The Pile)

Max Activating Token Index: 302

Text #7

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2704. Min Act: -0.0000

Data Index: 745214 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2508. Min Act: -0.0000

Data Index: 1913363 (The Pile)

Max Activating Token Index: 939

Text #9

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2500. Min Act: -0.0000

Data Index: 144804 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1823579 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2393. Min Act: -0.0000

Data Index: 902005 (The Pile)

Max Activating Token Index: 78

Text #12

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2647. Min Act: -0.0000

Data Index: 29230 (The Pile)

Max Activating Token Index: 678

Text #13

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2431. Min Act: -0.0000

Data Index: 831690 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1050633 (The Pile)

Max Activating Token Index: 486

Text #15

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2361. Min Act: -0.0000

Data Index: 441898 (The Pile)

Max Activating Token Index: 747

Text #16

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1149165 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1903977 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1043502 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1136106 (The Pile)

Max Activating Token Index: 957