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

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

Neuron 1949 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.7109. Min Act: -0.0001

Data Index: 780317 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.7069. Min Act: -0.0000

Data Index: 1227800 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6488. Min Act: -0.0000

Data Index: 236463 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6412. Min Act: -0.0001

Data Index: 494494 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6582. Min Act: -0.0001

Data Index: 602488 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6347. Min Act: 0.0001

Data Index: 138073 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6084. Min Act: 0.0001

Data Index: 261796 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6154. Min Act: 0.0002

Data Index: 1164040 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6345. Min Act: -0.0000

Data Index: 213919 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6459. Min Act: -0.0001

Data Index: 734342 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5860. Min Act: 0.0001

Data Index: 397178 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5873. Min Act: -0.0001

Data Index: 1101737 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6025. Min Act: -0.0001

Data Index: 708583 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5939. Min Act: -0.0000

Data Index: 6577 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5801. Min Act: -0.0001

Data Index: 459396 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5971. Min Act: -0.0001

Data Index: 1105889 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1050945 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5457. Min Act: -0.0001

Data Index: 1225438 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5595. Min Act: -0.0001

Data Index: 303288 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5573. Min Act: -0.0000

Data Index: 494320 (C4 (Web Text))

Max Activating Token Index: 364