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

Dataset: The Pile

Neuron 2474 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: 1.8522. Min Range: -1.8522

Max Act: 1.8522. Min Act: -0.0000

Data Index: 259102 (The Pile)

Max Activating Token Index: 446

Text #1

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.5494. Min Act: -0.0000

Data Index: 548496 (The Pile)

Max Activating Token Index: 96

Text #2

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.3708. Min Act: -0.0000

Data Index: 944301 (The Pile)

Max Activating Token Index: 112

Text #3

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1234243 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.4335. Min Act: -0.0000

Data Index: 833354 (The Pile)

Max Activating Token Index: 867

Text #5

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.2271. Min Act: -0.0000

Data Index: 396852 (The Pile)

Max Activating Token Index: 497

Text #6

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.2189. Min Act: -0.0000

Data Index: 911647 (The Pile)

Max Activating Token Index: 878

Text #7

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.1035. Min Act: -0.0000

Data Index: 1532051 (The Pile)

Max Activating Token Index: 721

Text #8

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.1084. Min Act: -0.0000

Data Index: 442321 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1253506 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.1011. Min Act: -0.0000

Data Index: 599105 (The Pile)

Max Activating Token Index: 400

Text #11

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.0389. Min Act: -0.0000

Data Index: 505239 (The Pile)

Max Activating Token Index: 151

Text #12

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.0593. Min Act: -0.0000

Data Index: 646633 (The Pile)

Max Activating Token Index: 777

Text #13

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.1236. Min Act: -0.0000

Data Index: 1993371 (The Pile)

Max Activating Token Index: 747

Text #14

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.0195. Min Act: -0.0000

Data Index: 909505 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.0988. Min Act: -0.0000

Data Index: 1619539 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.0936. Min Act: -0.0000

Data Index: 91693 (The Pile)

Max Activating Token Index: 355

Text #17

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.1642. Min Act: -0.0000

Data Index: 153230 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.0331. Min Act: -0.0000

Data Index: 118125 (The Pile)

Max Activating Token Index: 819

Text #19

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.0922. Min Act: -0.0000

Data Index: 1838455 (The Pile)

Max Activating Token Index: 274