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

Dataset: The Pile

Neuron 2284 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1992589 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1740340 (The Pile)

Max Activating Token Index: 213

Text #2

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3539. Min Act: -0.0000

Data Index: 646648 (The Pile)

Max Activating Token Index: 151

Text #3

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3375. Min Act: -0.0000

Data Index: 869591 (The Pile)

Max Activating Token Index: 64

Text #4

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1862421 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1444233 (The Pile)

Max Activating Token Index: 212

Text #6

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3385. Min Act: -0.0000

Data Index: 254128 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1779038 (The Pile)

Max Activating Token Index: 129

Text #8

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3146. Min Act: -0.0000

Data Index: 435562 (The Pile)

Max Activating Token Index: 132

Text #9

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3350. Min Act: -0.0000

Data Index: 700585 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1474419 (The Pile)

Max Activating Token Index: 115

Text #11

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3090. Min Act: -0.0000

Data Index: 979650 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3152. Min Act: -0.0000

Data Index: 8665 (The Pile)

Max Activating Token Index: 588

Text #13

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3067. Min Act: -0.0000

Data Index: 743433 (The Pile)

Max Activating Token Index: 833

Text #14

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1727142 (The Pile)

Max Activating Token Index: 671

Text #15

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3073. Min Act: -0.0000

Data Index: 995055 (The Pile)

Max Activating Token Index: 288

Text #16

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3145. Min Act: -0.0000

Data Index: 455131 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1017027 (The Pile)

Max Activating Token Index: 321

Text #18

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3132. Min Act: -0.0000

Data Index: 971659 (The Pile)

Max Activating Token Index: 508

Text #19

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3209. Min Act: -0.0000

Data Index: 40700 (The Pile)

Max Activating Token Index: 290