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

Dataset: The Pile

Neuron 4339 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.7250. Min Act: -0.0000

Data Index: 498166 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1870820 (The Pile)

Max Activating Token Index: 750

Text #2

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1250672 (The Pile)

Max Activating Token Index: 372

Text #3

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1491346 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.4840. Min Act: -0.0000

Data Index: 584912 (The Pile)

Max Activating Token Index: 810

Text #5

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1432067 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1291768 (The Pile)

Max Activating Token Index: 688

Text #7

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.4742. Min Act: -0.0000

Data Index: 150613 (The Pile)

Max Activating Token Index: 890

Text #8

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.4724. Min Act: -0.0000

Data Index: 857154 (The Pile)

Max Activating Token Index: 960

Text #9

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.4512. Min Act: -0.0000

Data Index: 655189 (The Pile)

Max Activating Token Index: 724

Text #10

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1642109 (The Pile)

Max Activating Token Index: 919

Text #11

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.4034. Min Act: -0.0000

Data Index: 145342 (The Pile)

Max Activating Token Index: 597

Text #12

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1415427 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.4262. Min Act: -0.0000

Data Index: 17489 (The Pile)

Max Activating Token Index: 412

Text #14

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3981. Min Act: -0.0000

Data Index: 822449 (The Pile)

Max Activating Token Index: 591

Text #15

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3753. Min Act: -0.0000

Data Index: 596283 (The Pile)

Max Activating Token Index: 939

Text #16

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1901698 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1092817 (The Pile)

Max Activating Token Index: 502

Text #18

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3552. Min Act: -0.0000

Data Index: 916746 (The Pile)

Max Activating Token Index: 436

Text #19

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1490261 (The Pile)

Max Activating Token Index: 931