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

Dataset: The Pile

Neuron 2212 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: 0.3636. Min Range: -0.3636

Max Act: 0.3636. Min Act: -0.0000

Data Index: 331792 (The Pile)

Max Activating Token Index: 875

Text #1

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3379. Min Act: -0.0000

Data Index: 838376 (The Pile)

Max Activating Token Index: 428

Text #2

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1908288 (The Pile)

Max Activating Token Index: 242

Text #3

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2633. Min Act: -0.0000

Data Index: 460814 (The Pile)

Max Activating Token Index: 683

Text #4

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1746148 (The Pile)

Max Activating Token Index: 114

Text #5

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1967708 (The Pile)

Max Activating Token Index: 82

Text #6

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2669. Min Act: -0.0000

Data Index: 914672 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2562. Min Act: -0.0000

Data Index: 612189 (The Pile)

Max Activating Token Index: 60

Text #8

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2220. Min Act: -0.0000

Data Index: 653089 (The Pile)

Max Activating Token Index: 19

Text #9

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1033380 (The Pile)

Max Activating Token Index: 285

Text #10

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1906274 (The Pile)

Max Activating Token Index: 215

Text #11

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1549200 (The Pile)

Max Activating Token Index: 625

Text #12

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1481063 (The Pile)

Max Activating Token Index: 512

Text #13

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2279. Min Act: -0.0000

Data Index: 731167 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1518279 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1072956 (The Pile)

Max Activating Token Index: 981

Text #16

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2132. Min Act: -0.0000

Data Index: 336670 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2328. Min Act: -0.0000

Data Index: 671410 (The Pile)

Max Activating Token Index: 396

Text #18

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2051. Min Act: -0.0000

Data Index: 167779 (The Pile)

Max Activating Token Index: 10

Text #19

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1365025 (The Pile)

Max Activating Token Index: 331