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

Dataset: The Pile

Neuron 2895 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.7582. Min Act: -0.0000

Data Index: 519403 (The Pile)

Max Activating Token Index: 252

Text #1

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.6649. Min Act: -0.0000

Data Index: 1051132 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.5992. Min Act: -0.0000

Data Index: 1717049 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.5546. Min Act: -0.0000

Data Index: 644556 (The Pile)

Max Activating Token Index: 517

Text #4

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.5170. Min Act: -0.0000

Data Index: 643617 (The Pile)

Max Activating Token Index: 350

Text #5

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.4256. Min Act: -0.0000

Data Index: 814756 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.4947. Min Act: -0.0000

Data Index: 188459 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1657127 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.5610. Min Act: -0.0000

Data Index: 12801 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.4932. Min Act: -0.0000

Data Index: 638311 (The Pile)

Max Activating Token Index: 215

Text #10

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.4866. Min Act: -0.0000

Data Index: 1707610 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.4735. Min Act: -0.0000

Data Index: 350273 (The Pile)

Max Activating Token Index: 746

Text #12

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.3914. Min Act: -0.0000

Data Index: 766199 (The Pile)

Max Activating Token Index: 103

Text #13

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.2874. Min Act: -0.0000

Data Index: 255016 (The Pile)

Max Activating Token Index: 880

Text #14

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.4268. Min Act: -0.0000

Data Index: 701729 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.5188. Min Act: -0.0000

Data Index: 1443977 (The Pile)

Max Activating Token Index: 298

Text #16

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.3407. Min Act: -0.0000

Data Index: 118644 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.3386. Min Act: -0.0000

Data Index: 178587 (The Pile)

Max Activating Token Index: 267

Text #18

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.4161. Min Act: -0.0000

Data Index: 175070 (The Pile)

Max Activating Token Index: 350

Text #19

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.4193. Min Act: -0.0000

Data Index: 789272 (The Pile)

Max Activating Token Index: 539