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

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

Neuron 367 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6987. Min Act: -0.0001

Data Index: 1345094 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6356. Min Act: -0.0001

Data Index: 718308 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6750. Min Act: -0.0001

Data Index: 977178 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.6298. Min Act: -0.0001

Data Index: 1020445 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5835. Min Act: -0.0001

Data Index: 660554 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5958. Min Act: -0.0001

Data Index: 1197431 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5921. Min Act: -0.0001

Data Index: 193400 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5947. Min Act: -0.0001

Data Index: 561143 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5794. Min Act: -0.0001

Data Index: 1208084 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5740. Min Act: -0.0001

Data Index: 601664 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5335. Min Act: -0.0001

Data Index: 1254882 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5495. Min Act: -0.0001

Data Index: 538684 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5613. Min Act: -0.0001

Data Index: 152627 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5314. Min Act: -0.0001

Data Index: 249308 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5491. Min Act: -0.0001

Data Index: 963982 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5236. Min Act: -0.0001

Data Index: 1195518 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5365. Min Act: -0.0001

Data Index: 806998 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5193. Min Act: -0.0001

Data Index: 625706 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.4874. Min Act: -0.0001

Data Index: 922110 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.6987. Min Range: -0.6987

Max Act: 0.5129. Min Act: -0.0001

Data Index: 667825 (C4 (Web Text))

Max Activating Token Index: 289