Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 382 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3941. Min Act: 0.0000

Data Index: 1630840 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3882. Min Act: -0.0000

Data Index: 876539 (The Pile)

Max Activating Token Index: 258

Text #2

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1061160 (The Pile)

Max Activating Token Index: 624

Text #3

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1968434 (The Pile)

Max Activating Token Index: 459

Text #4

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1588069 (The Pile)

Max Activating Token Index: 834

Text #5

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1682842 (The Pile)

Max Activating Token Index: 339

Text #6

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3259. Min Act: -0.0000

Data Index: 1438849 (The Pile)

Max Activating Token Index: 938

Text #7

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1989095 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3159. Min Act: -0.0000

Data Index: 184960 (The Pile)

Max Activating Token Index: 349

Text #9

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3171. Min Act: -0.0000

Data Index: 234604 (The Pile)

Max Activating Token Index: 22

Text #10

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3178. Min Act: -0.0000

Data Index: 220211 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1048635 (The Pile)

Max Activating Token Index: 537

Text #12

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3069. Min Act: 0.0000

Data Index: 1985279 (The Pile)

Max Activating Token Index: 915

Text #13

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1367140 (The Pile)

Max Activating Token Index: 125

Text #14

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1325071 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1344756 (The Pile)

Max Activating Token Index: 999

Text #16

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2972. Min Act: -0.0000

Data Index: 393723 (The Pile)

Max Activating Token Index: 316

Text #17

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1570448 (The Pile)

Max Activating Token Index: 396

Text #18

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2774. Min Act: -0.0000

Data Index: 369024 (The Pile)

Max Activating Token Index: 808

Text #19

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1828374 (The Pile)

Max Activating Token Index: 327