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

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

Neuron 3626 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8790. Min Act: -0.0001

Data Index: 1507191 (Python Code)

Max Activating Token Index: 654

Text #1

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8530. Min Act: -0.0000

Data Index: 785341 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8175. Min Act: -0.0001

Data Index: 1604891 (Python Code)

Max Activating Token Index: 785

Text #3

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8302. Min Act: -0.0001

Data Index: 257926 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1228430 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7524. Min Act: -0.0000

Data Index: 733735 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7469. Min Act: -0.0001

Data Index: 509519 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7960. Min Act: -0.0000

Data Index: 693368 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7357. Min Act: -0.0001

Data Index: 1407182 (Python Code)

Max Activating Token Index: 328

Text #9

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7972. Min Act: -0.0001

Data Index: 1516284 (Python Code)

Max Activating Token Index: 823

Text #10

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7483. Min Act: -0.0001

Data Index: 1313882 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1300774 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7580. Min Act: -0.0001

Data Index: 1602089 (Python Code)

Max Activating Token Index: 977

Text #13

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7541. Min Act: -0.0001

Data Index: 1521648 (Python Code)

Max Activating Token Index: 117

Text #14

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.6936. Min Act: -0.0000

Data Index: 953905 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.6711. Min Act: -0.0000

Data Index: 67790 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7106. Min Act: -0.0000

Data Index: 866365 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7092. Min Act: -0.0000

Data Index: 1087745 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7002. Min Act: -0.0001

Data Index: 1188026 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.6710. Min Act: -0.0001

Data Index: 463474 (C4 (Web Text))

Max Activating Token Index: 564