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

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

Neuron 4786 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: 0.6426. Min Range: -0.6426

Max Act: 0.6426. Min Act: -0.0000

Data Index: 117904 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.4057. Min Act: -0.0000

Data Index: 428537 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.3531. Min Act: -0.0000

Data Index: 38533 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.3339. Min Act: -0.0000

Data Index: 45151 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.3211. Min Act: -0.0000

Data Index: 320350 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.3194. Min Act: -0.0000

Data Index: 636618 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1047978 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.3006. Min Act: -0.0000

Data Index: 544048 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.3116. Min Act: -0.0000

Data Index: 423450 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.3106. Min Act: -0.0000

Data Index: 533798 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.2990. Min Act: 0.0000

Data Index: 711100 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.3050. Min Act: -0.0000

Data Index: 659163 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.2849. Min Act: -0.0000

Data Index: 774706 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.2850. Min Act: 0.0001

Data Index: 459751 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.3135. Min Act: -0.0000

Data Index: 574610 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.2836. Min Act: -0.0000

Data Index: 923466 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.2832. Min Act: 0.0001

Data Index: 1210489 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.2903. Min Act: -0.0000

Data Index: 537663 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.2974. Min Act: -0.0000

Data Index: 516916 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.2858. Min Act: -0.0000

Data Index: 580861 (C4 (Web Text))

Max Activating Token Index: 548