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

Dataset: The Pile

Neuron 3121 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: 1.7949. Min Range: -1.7949

Max Act: 1.7949. Min Act: -0.0000

Data Index: 196346 (The Pile)

Max Activating Token Index: 818

Text #1

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.4818. Min Act: -0.0000

Data Index: 728833 (The Pile)

Max Activating Token Index: 848

Text #2

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.4883. Min Act: -0.0000

Data Index: 1597173 (The Pile)

Max Activating Token Index: 661

Text #3

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.3269. Min Act: -0.0000

Data Index: 572370 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.4127. Min Act: -0.0000

Data Index: 634821 (The Pile)

Max Activating Token Index: 875

Text #5

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.2663. Min Act: -0.0000

Data Index: 178402 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.3285. Min Act: -0.0000

Data Index: 2795 (The Pile)

Max Activating Token Index: 26

Text #7

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.3145. Min Act: -0.0000

Data Index: 721236 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.3986. Min Act: -0.0000

Data Index: 1306158 (The Pile)

Max Activating Token Index: 916

Text #9

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.1391. Min Act: -0.0000

Data Index: 458907 (The Pile)

Max Activating Token Index: 22

Text #10

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1602145 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.3246. Min Act: -0.0000

Data Index: 1041352 (The Pile)

Max Activating Token Index: 500

Text #12

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.3822. Min Act: -0.0000

Data Index: 1465577 (The Pile)

Max Activating Token Index: 802

Text #13

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.1016. Min Act: -0.0000

Data Index: 408853 (The Pile)

Max Activating Token Index: 792

Text #14

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.3386. Min Act: -0.0000

Data Index: 1566743 (The Pile)

Max Activating Token Index: 613

Text #15

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.3513. Min Act: -0.0000

Data Index: 551496 (The Pile)

Max Activating Token Index: 709

Text #16

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.4894. Min Act: -0.0000

Data Index: 114194 (The Pile)

Max Activating Token Index: 634

Text #17

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.2745. Min Act: -0.0000

Data Index: 548158 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.2555. Min Act: -0.0000

Data Index: 358127 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 1.7949. Min Range: -1.7949

Max Act: 1.3237. Min Act: -0.0000

Data Index: 1847888 (The Pile)

Max Activating Token Index: 778