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

Dataset: The Pile

Neuron 2525 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.8593. Min Act: -0.0000

Data Index: 136435 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1134356 (The Pile)

Max Activating Token Index: 405

Text #2

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7725. Min Act: -0.0000

Data Index: 338042 (The Pile)

Max Activating Token Index: 255

Text #3

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7221. Min Act: -0.0000

Data Index: 92777 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1155892 (The Pile)

Max Activating Token Index: 489

Text #5

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1211228 (The Pile)

Max Activating Token Index: 345

Text #6

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1579162 (The Pile)

Max Activating Token Index: 304

Text #7

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7009. Min Act: -0.0000

Data Index: 1838864 (The Pile)

Max Activating Token Index: 443

Text #8

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7611. Min Act: -0.0000

Data Index: 1692790 (The Pile)

Max Activating Token Index: 411

Text #9

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1229183 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6279. Min Act: -0.0000

Data Index: 779245 (The Pile)

Max Activating Token Index: 195

Text #11

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6592. Min Act: -0.0000

Data Index: 426455 (The Pile)

Max Activating Token Index: 214

Text #12

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6289. Min Act: -0.0000

Data Index: 1340015 (The Pile)

Max Activating Token Index: 164

Text #13

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1429365 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1011655 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1226168 (The Pile)

Max Activating Token Index: 430

Text #16

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.5932. Min Act: -0.0000

Data Index: 344705 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.5746. Min Act: -0.0000

Data Index: 722175 (The Pile)

Max Activating Token Index: 870

Text #18

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1245210 (The Pile)

Max Activating Token Index: 359

Text #19

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6268. Min Act: -0.0000

Data Index: 491272 (The Pile)

Max Activating Token Index: 588