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

Dataset: The Pile

Neuron 4394 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1449290 (The Pile)

Max Activating Token Index: 824

Text #1

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3454. Min Act: -0.0000

Data Index: 792432 (The Pile)

Max Activating Token Index: 229

Text #2

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1438724 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3465. Min Act: -0.0000

Data Index: 700811 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1788674 (The Pile)

Max Activating Token Index: 429

Text #5

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3322. Min Act: -0.0000

Data Index: 201704 (The Pile)

Max Activating Token Index: 131

Text #6

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3284. Min Act: -0.0000

Data Index: 897717 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1635146 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.2975. Min Act: -0.0000

Data Index: 756474 (The Pile)

Max Activating Token Index: 832

Text #9

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1374060 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3293. Min Act: -0.0000

Data Index: 1600456 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3195. Min Act: -0.0000

Data Index: 1956834 (The Pile)

Max Activating Token Index: 576

Text #12

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1006790 (The Pile)

Max Activating Token Index: 189

Text #13

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3375. Min Act: -0.0000

Data Index: 475475 (The Pile)

Max Activating Token Index: 799

Text #14

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3056. Min Act: -0.0000

Data Index: 43027 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1711650 (The Pile)

Max Activating Token Index: 383

Text #16

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3116. Min Act: -0.0000

Data Index: 911147 (The Pile)

Max Activating Token Index: 182

Text #17

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3326. Min Act: -0.0000

Data Index: 565134 (The Pile)

Max Activating Token Index: 800

Text #18

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.2796. Min Act: -0.0000

Data Index: 899500 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 0.3831. Min Range: -0.3831

Max Act: 0.3097. Min Act: -0.0000

Data Index: 338479 (The Pile)

Max Activating Token Index: 381