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

Dataset: The Pile

Neuron 1151 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.3175. Min Act: -0.0000

Data Index: 26969 (The Pile)

Max Activating Token Index: 73

Text #1

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.3088. Min Act: -0.0000

Data Index: 355382 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2328. Min Act: -0.0000

Data Index: 894117 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1851184 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2675. Min Act: -0.0000

Data Index: 240644 (The Pile)

Max Activating Token Index: 482

Text #5

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2494. Min Act: -0.0000

Data Index: 369682 (The Pile)

Max Activating Token Index: 583

Text #6

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1064637 (The Pile)

Max Activating Token Index: 572

Text #7

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2461. Min Act: -0.0000

Data Index: 954667 (The Pile)

Max Activating Token Index: 644

Text #8

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2765. Min Act: -0.0000

Data Index: 692430 (The Pile)

Max Activating Token Index: 718

Text #9

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2551. Min Act: -0.0000

Data Index: 871603 (The Pile)

Max Activating Token Index: 460

Text #10

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1159431 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2410. Min Act: -0.0000

Data Index: 659611 (The Pile)

Max Activating Token Index: 924

Text #12

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2387. Min Act: -0.0000

Data Index: 224163 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1973084 (The Pile)

Max Activating Token Index: 455

Text #14

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.1875. Min Act: -0.0000

Data Index: 1333069 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2332. Min Act: -0.0000

Data Index: 301032 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2237. Min Act: -0.0000

Data Index: 569745 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1579359 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1651348 (The Pile)

Max Activating Token Index: 394

Text #19

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1194395 (The Pile)

Max Activating Token Index: 1001