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

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

Neuron 454 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.5261. Min Act: -0.0000

Data Index: 1232089 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.2086. Min Act: -0.0000

Data Index: 539593 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0949. Min Act: -0.0000

Data Index: 460732 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1539. Min Act: -0.0000

Data Index: 142418 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1163. Min Act: -0.0000

Data Index: 1427635 (Python Code)

Max Activating Token Index: 118

Text #5

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0587. Min Act: -0.0000

Data Index: 525066 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 1.5261. Min Range: -1.5261

Max Act: 0.9970. Min Act: 0.0001

Data Index: 1024353 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1178653 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0619. Min Act: -0.0000

Data Index: 94211 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.5261. Min Range: -1.5261

Max Act: 0.9878. Min Act: -0.0000

Data Index: 1206489 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 1.5261. Min Range: -1.5261

Max Act: 0.9512. Min Act: -0.0000

Data Index: 894508 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0116. Min Act: -0.0000

Data Index: 1535188 (Python Code)

Max Activating Token Index: 698

Text #12

Max Range: 1.5261. Min Range: -1.5261

Max Act: 0.9850. Min Act: -0.0000

Data Index: 238187 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 1.5261. Min Range: -1.5261

Max Act: 0.9850. Min Act: -0.0000

Data Index: 483429 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 1.5261. Min Range: -1.5261

Max Act: 0.9520. Min Act: -0.0000

Data Index: 227021 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 1.5261. Min Range: -1.5261

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1425786 (Python Code)

Max Activating Token Index: 127

Text #16

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0380. Min Act: -0.0000

Data Index: 331605 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 1.5261. Min Range: -1.5261

Max Act: 0.9766. Min Act: -0.0000

Data Index: 283003 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1411027 (Python Code)

Max Activating Token Index: 790

Text #19

Max Range: 1.5261. Min Range: -1.5261

Max Act: 0.9408. Min Act: -0.0000

Data Index: 638773 (C4 (Web Text))

Max Activating Token Index: 768