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

Dataset: The Pile

Neuron 1900 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: 0.3711. Min Range: -0.3711

Max Act: 0.3474. Min Act: -0.0000

Data Index: 440320 (The Pile)

Max Activating Token Index: 76

Text #1

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1757464 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1098231 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3251. Min Act: -0.0000

Data Index: 974855 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3123. Min Act: -0.0000

Data Index: 832367 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1594375 (The Pile)

Max Activating Token Index: 362

Text #6

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1299007 (The Pile)

Max Activating Token Index: 760

Text #7

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3073. Min Act: -0.0000

Data Index: 698446 (The Pile)

Max Activating Token Index: 557

Text #8

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3098. Min Act: -0.0000

Data Index: 888114 (The Pile)

Max Activating Token Index: 288

Text #9

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3012. Min Act: -0.0000

Data Index: 588155 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1834260 (The Pile)

Max Activating Token Index: 298

Text #11

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1200094 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1947984 (The Pile)

Max Activating Token Index: 464

Text #13

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2702. Min Act: -0.0000

Data Index: 311904 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1441660 (The Pile)

Max Activating Token Index: 666

Text #15

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1334813 (The Pile)

Max Activating Token Index: 812

Text #16

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2750. Min Act: -0.0000

Data Index: 331108 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1125091 (The Pile)

Max Activating Token Index: 459

Text #18

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2953. Min Act: -0.0000

Data Index: 700064 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2914. Min Act: -0.0000

Data Index: 399537 (The Pile)

Max Activating Token Index: 851