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

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

Neuron 4077 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2487. Min Range: -1.2487

Max Act: 1.2487. Min Act: -0.0001

Data Index: 340449 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 1.2487. Min Range: -1.2487

Max Act: 1.1988. Min Act: -0.0001

Data Index: 50847 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 1.2487. Min Range: -1.2487

Max Act: 1.1347. Min Act: -0.0001

Data Index: 537009 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 1.2487. Min Range: -1.2487

Max Act: 1.1126. Min Act: -0.0001

Data Index: 1002986 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 1.2487. Min Range: -1.2487

Max Act: 1.0561. Min Act: -0.0001

Data Index: 571288 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 1.2487. Min Range: -1.2487

Max Act: 0.9959. Min Act: -0.0001

Data Index: 536993 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 1.2487. Min Range: -1.2487

Max Act: 1.0107. Min Act: -0.0001

Data Index: 718757 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 1.2487. Min Range: -1.2487

Max Act: 1.0386. Min Act: -0.0001

Data Index: 960702 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 1.2487. Min Range: -1.2487

Max Act: 1.0322. Min Act: -0.0001

Data Index: 262828 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 1.2487. Min Range: -1.2487

Max Act: 1.0301. Min Act: -0.0001

Data Index: 1106557 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 1.2487. Min Range: -1.2487

Max Act: 0.9240. Min Act: -0.0001

Data Index: 149765 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 1.2487. Min Range: -1.2487

Max Act: 1.0343. Min Act: -0.0001

Data Index: 847331 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 1.2487. Min Range: -1.2487

Max Act: 1.0089. Min Act: -0.0001

Data Index: 971009 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 1.2487. Min Range: -1.2487

Max Act: 0.8568. Min Act: -0.0001

Data Index: 1272226 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 1.2487. Min Range: -1.2487

Max Act: 0.8467. Min Act: -0.0001

Data Index: 697293 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 1.2487. Min Range: -1.2487

Max Act: 0.8639. Min Act: -0.0001

Data Index: 508618 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 1.2487. Min Range: -1.2487

Max Act: 0.8970. Min Act: -0.0001

Data Index: 179843 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 1.2487. Min Range: -1.2487

Max Act: 0.8649. Min Act: -0.0001

Data Index: 307442 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 1.2487. Min Range: -1.2487

Max Act: 0.7801. Min Act: -0.0001

Data Index: 905213 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 1.2487. Min Range: -1.2487

Max Act: 0.8256. Min Act: -0.0001

Data Index: 998443 (C4 (Web Text))

Max Activating Token Index: 795