Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1844 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.8400. Min Act: -0.0000

Data Index: 179892 (The Pile)

Max Activating Token Index: 351

Text #1

Max Range: 3.8400. Min Range: -3.8400

Max Act: 2.9047. Min Act: -0.0000

Data Index: 36257 (The Pile)

Max Activating Token Index: 174

Text #2

Max Range: 3.8400. Min Range: -3.8400

Max Act: 2.2214. Min Act: -0.0000

Data Index: 571442 (The Pile)

Max Activating Token Index: 47

Text #3

Max Range: 3.8400. Min Range: -3.8400

Max Act: 2.0769. Min Act: -0.0000

Data Index: 386668 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 3.8400. Min Range: -3.8400

Max Act: 2.2266. Min Act: -0.0000

Data Index: 822104 (The Pile)

Max Activating Token Index: 298

Text #5

Max Range: 3.8400. Min Range: -3.8400

Max Act: 2.1625. Min Act: -0.0000

Data Index: 1423961 (The Pile)

Max Activating Token Index: 873

Text #6

Max Range: 3.8400. Min Range: -3.8400

Max Act: 2.0353. Min Act: -0.0000

Data Index: 910707 (The Pile)

Max Activating Token Index: 126

Text #7

Max Range: 3.8400. Min Range: -3.8400

Max Act: 2.1352. Min Act: -0.0000

Data Index: 743746 (The Pile)

Max Activating Token Index: 200

Text #8

Max Range: 3.8400. Min Range: -3.8400

Max Act: 1.9876. Min Act: -0.0000

Data Index: 1801714 (The Pile)

Max Activating Token Index: 210

Text #9

Max Range: 3.8400. Min Range: -3.8400

Max Act: 1.8847. Min Act: -0.0000

Data Index: 1646471 (The Pile)

Max Activating Token Index: 334

Text #10

Max Range: 3.8400. Min Range: -3.8400

Max Act: 1.9903. Min Act: -0.0000

Data Index: 1374244 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 3.8400. Min Range: -3.8400

Max Act: 1.9564. Min Act: -0.0000

Data Index: 1347596 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 3.8400. Min Range: -3.8400

Max Act: 1.9261. Min Act: -0.0000

Data Index: 1721289 (The Pile)

Max Activating Token Index: 283

Text #13

Max Range: 3.8400. Min Range: -3.8400

Max Act: 2.0249. Min Act: -0.0000

Data Index: 1443734 (The Pile)

Max Activating Token Index: 169

Text #14

Max Range: 3.8400. Min Range: -3.8400

Max Act: 1.7469. Min Act: -0.0000

Data Index: 192473 (The Pile)

Max Activating Token Index: 215

Text #15

Max Range: 3.8400. Min Range: -3.8400

Max Act: 1.7669. Min Act: -0.0000

Data Index: 1713761 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 3.8400. Min Range: -3.8400

Max Act: 2.2207. Min Act: -0.0000

Data Index: 1942614 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 3.8400. Min Range: -3.8400

Max Act: 1.6898. Min Act: -0.0000

Data Index: 1974178 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 3.8400. Min Range: -3.8400

Max Act: 1.8892. Min Act: -0.0000

Data Index: 593273 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 3.8400. Min Range: -3.8400

Max Act: 1.7479. Min Act: -0.0000

Data Index: 564382 (The Pile)

Max Activating Token Index: 310