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

Dataset: The Pile

Neuron 375 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: 0.3800. Min Range: -0.3800

Max Act: 0.3766. Min Act: -0.0000

Data Index: 273750 (The Pile)

Max Activating Token Index: 537

Text #1

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3800. Min Act: -0.0000

Data Index: 800719 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1684392 (The Pile)

Max Activating Token Index: 361

Text #3

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1371225 (The Pile)

Max Activating Token Index: 657

Text #4

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3486. Min Act: -0.0000

Data Index: 318431 (The Pile)

Max Activating Token Index: 957

Text #5

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3125. Min Act: -0.0000

Data Index: 674511 (The Pile)

Max Activating Token Index: 565

Text #6

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2985. Min Act: -0.0000

Data Index: 395194 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1381402 (The Pile)

Max Activating Token Index: 798

Text #8

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3173. Min Act: -0.0000

Data Index: 233036 (The Pile)

Max Activating Token Index: 967

Text #9

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3025. Min Act: -0.0000

Data Index: 377949 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3153. Min Act: -0.0000

Data Index: 797149 (The Pile)

Max Activating Token Index: 566

Text #11

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1734326 (The Pile)

Max Activating Token Index: 57

Text #12

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1682618 (The Pile)

Max Activating Token Index: 328

Text #13

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1144192 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1214438 (The Pile)

Max Activating Token Index: 183

Text #15

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1744990 (The Pile)

Max Activating Token Index: 340

Text #16

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2989. Min Act: -0.0000

Data Index: 674262 (The Pile)

Max Activating Token Index: 659

Text #17

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2868. Min Act: -0.0000

Data Index: 190969 (The Pile)

Max Activating Token Index: 345

Text #18

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2982. Min Act: -0.0000

Data Index: 714475 (The Pile)

Max Activating Token Index: 133

Text #19

Max Range: 0.3800. Min Range: -0.3800

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1905926 (The Pile)

Max Activating Token Index: 34