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

Dataset: The Pile

Neuron 4234 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: 1.7160. Min Range: -1.7160

Max Act: 1.7160. Min Act: -0.0000

Data Index: 1711720 (The Pile)

Max Activating Token Index: 921

Text #1

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.4976. Min Act: -0.0000

Data Index: 820592 (The Pile)

Max Activating Token Index: 532

Text #2

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.3581. Min Act: -0.0000

Data Index: 751028 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.3099. Min Act: -0.0000

Data Index: 925198 (The Pile)

Max Activating Token Index: 273

Text #4

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1398776 (The Pile)

Max Activating Token Index: 77

Text #5

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.1985. Min Act: -0.0000

Data Index: 368293 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.2995. Min Act: -0.0000

Data Index: 1309491 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.3345. Min Act: -0.0000

Data Index: 689716 (The Pile)

Max Activating Token Index: 896

Text #8

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.2459. Min Act: -0.0000

Data Index: 1135990 (The Pile)

Max Activating Token Index: 611

Text #9

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.3098. Min Act: -0.0000

Data Index: 1116253 (The Pile)

Max Activating Token Index: 636

Text #10

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.3326. Min Act: -0.0000

Data Index: 839032 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.2844. Min Act: -0.0000

Data Index: 1347674 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.3240. Min Act: -0.0000

Data Index: 1236029 (The Pile)

Max Activating Token Index: 431

Text #13

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.3408. Min Act: -0.0000

Data Index: 920221 (The Pile)

Max Activating Token Index: 964

Text #14

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.2357. Min Act: -0.0000

Data Index: 941495 (The Pile)

Max Activating Token Index: 808

Text #15

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.2619. Min Act: -0.0000

Data Index: 365922 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.2130. Min Act: -0.0000

Data Index: 248778 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.2140. Min Act: -0.0000

Data Index: 1022153 (The Pile)

Max Activating Token Index: 233

Text #18

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.1189. Min Act: -0.0000

Data Index: 1976332 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 1.7160. Min Range: -1.7160

Max Act: 1.1167. Min Act: -0.0000

Data Index: 1237831 (The Pile)

Max Activating Token Index: 166