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

Dataset: The Pile

Neuron 4039 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1876245 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1315001 (The Pile)

Max Activating Token Index: 20

Text #2

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1346594 (The Pile)

Max Activating Token Index: 17

Text #3

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3839. Min Act: -0.0000

Data Index: 497134 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3632. Min Act: 0.0000

Data Index: 577867 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1520249 (The Pile)

Max Activating Token Index: 16

Text #6

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3263. Min Act: -0.0000

Data Index: 1068957 (The Pile)

Max Activating Token Index: 182

Text #7

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3428. Min Act: -0.0000

Data Index: 118454 (The Pile)

Max Activating Token Index: 53

Text #8

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3067. Min Act: -0.0000

Data Index: 1259341 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3407. Min Act: -0.0000

Data Index: 24843 (The Pile)

Max Activating Token Index: 87

Text #10

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1405744 (The Pile)

Max Activating Token Index: 81

Text #11

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1031671 (The Pile)

Max Activating Token Index: 23

Text #12

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3022. Min Act: -0.0000

Data Index: 148823 (The Pile)

Max Activating Token Index: 60

Text #13

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1005267 (The Pile)

Max Activating Token Index: 42

Text #14

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1062064 (The Pile)

Max Activating Token Index: 58

Text #15

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3084. Min Act: -0.0000

Data Index: 754074 (The Pile)

Max Activating Token Index: 22

Text #16

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3222. Min Act: -0.0000

Data Index: 663950 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1856631 (The Pile)

Max Activating Token Index: 82

Text #18

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.2998. Min Act: -0.0000

Data Index: 153287 (The Pile)

Max Activating Token Index: 19

Text #19

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1144449 (The Pile)

Max Activating Token Index: 152