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

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

Neuron 532 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1009884 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6215. Min Act: -0.0000

Data Index: 682691 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1261677 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6177. Min Act: -0.0000

Data Index: 402004 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6327. Min Act: -0.0000

Data Index: 693271 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6246. Min Act: -0.0000

Data Index: 203653 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5972. Min Act: -0.0000

Data Index: 999835 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6374. Min Act: -0.0000

Data Index: 1226819 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6017. Min Act: -0.0001

Data Index: 84634 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1063960 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5538. Min Act: -0.0000

Data Index: 222163 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1288567 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5660. Min Act: -0.0000

Data Index: 234206 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1231654 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6072. Min Act: -0.0000

Data Index: 760631 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6221. Min Act: -0.0000

Data Index: 609896 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5780. Min Act: -0.0000

Data Index: 819726 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5487. Min Act: -0.0000

Data Index: 808339 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5822. Min Act: -0.0000

Data Index: 856722 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.4987. Min Act: -0.0000

Data Index: 594181 (C4 (Web Text))

Max Activating Token Index: 7