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

Dataset: The Pile

Neuron 4593 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4041. Min Range: -1.4041

Max Act: 1.4041. Min Act: -0.0000

Data Index: 471890 (The Pile)

Max Activating Token Index: 642

Text #1

Max Range: 1.4041. Min Range: -1.4041

Max Act: 1.0755. Min Act: -0.0000

Data Index: 1384898 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 1.4041. Min Range: -1.4041

Max Act: 1.1183. Min Act: -0.0000

Data Index: 636694 (The Pile)

Max Activating Token Index: 334

Text #3

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1832060 (The Pile)

Max Activating Token Index: 160

Text #4

Max Range: 1.4041. Min Range: -1.4041

Max Act: 1.0257. Min Act: -0.0000

Data Index: 408110 (The Pile)

Max Activating Token Index: 305

Text #5

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.9579. Min Act: 0.0000

Data Index: 257702 (The Pile)

Max Activating Token Index: 503

Text #6

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1992845 (The Pile)

Max Activating Token Index: 526

Text #7

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1139370 (The Pile)

Max Activating Token Index: 353

Text #8

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.8411. Min Act: -0.0000

Data Index: 559532 (The Pile)

Max Activating Token Index: 379

Text #9

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.8313. Min Act: -0.0000

Data Index: 812957 (The Pile)

Max Activating Token Index: 961

Text #10

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1386800 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 1.4041. Min Range: -1.4041

Max Act: 1.0161. Min Act: -0.0000

Data Index: 516798 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.8590. Min Act: -0.0000

Data Index: 914023 (The Pile)

Max Activating Token Index: 773

Text #13

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1640544 (The Pile)

Max Activating Token Index: 571

Text #14

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.9381. Min Act: -0.0000

Data Index: 780018 (The Pile)

Max Activating Token Index: 639

Text #15

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.9148. Min Act: -0.0000

Data Index: 6716 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.8870. Min Act: 0.0001

Data Index: 1863547 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1155280 (The Pile)

Max Activating Token Index: 198

Text #18

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1381873 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 1.4041. Min Range: -1.4041

Max Act: 0.7687. Min Act: -0.0000

Data Index: 599577 (The Pile)

Max Activating Token Index: 371