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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4200 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.8956. Min Act: -0.0000

Data Index: 551448 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.5026. Min Act: -0.0000

Data Index: 115554 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.2213. Min Act: -0.0000

Data Index: 269473 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 2.8956. Min Range: -2.8956

Max Act: 1.9658. Min Act: -0.0000

Data Index: 211509 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.0242. Min Act: -0.0000

Data Index: 896919 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.1050. Min Act: -0.0000

Data Index: 1258143 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.2713. Min Act: -0.0000

Data Index: 435532 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.2000. Min Act: -0.0000

Data Index: 472945 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.0859. Min Act: -0.0000

Data Index: 993095 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.1417. Min Act: -0.0000

Data Index: 1100444 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.0856. Min Act: -0.0000

Data Index: 1132794 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 2.8956. Min Range: -2.8956

Max Act: 1.9506. Min Act: -0.0000

Data Index: 291815 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 2.8956. Min Range: -2.8956

Max Act: 1.9508. Min Act: -0.0000

Data Index: 673894 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.1133. Min Act: -0.0000

Data Index: 921193 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 2.8956. Min Range: -2.8956

Max Act: 1.9738. Min Act: -0.0000

Data Index: 254748 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 2.8956. Min Range: -2.8956

Max Act: 1.9486. Min Act: -0.0000

Data Index: 279740 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.1473. Min Act: -0.0000

Data Index: 497237 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.0502. Min Act: -0.0000

Data Index: 927888 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.0171. Min Act: -0.0000

Data Index: 1095120 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 2.8956. Min Range: -2.8956

Max Act: 2.0151. Min Act: -0.0000

Data Index: 307348 (C4 (Web Text))

Max Activating Token Index: 1022