Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1266 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1342. Min Range: -1.1342

Max Act: 1.1342. Min Act: -0.0000

Data Index: 1654356 (Python Code)

Max Activating Token Index: 267

Text #1

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8807. Min Act: -0.0000

Data Index: 145444 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8398. Min Act: -0.0000

Data Index: 1614301 (Python Code)

Max Activating Token Index: 679

Text #3

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.7887. Min Act: -0.0000

Data Index: 52581 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.7862. Min Act: -0.0000

Data Index: 523976 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1532370 (Python Code)

Max Activating Token Index: 109

Text #6

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1210751 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1133258 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.7169. Min Act: -0.0000

Data Index: 894508 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.7097. Min Act: -0.0000

Data Index: 921625 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1501922 (Python Code)

Max Activating Token Index: 940

Text #11

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1619394 (Python Code)

Max Activating Token Index: 413

Text #12

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.7492. Min Act: -0.0000

Data Index: 726608 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1340689 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1399353 (Python Code)

Max Activating Token Index: 252

Text #15

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1496911 (Python Code)

Max Activating Token Index: 223

Text #16

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1447174 (Python Code)

Max Activating Token Index: 771

Text #17

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1626929 (Python Code)

Max Activating Token Index: 829

Text #18

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1393504 (Python Code)

Max Activating Token Index: 829

Text #19

Max Range: 1.1342. Min Range: -1.1342

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1294782 (C4 (Web Text))

Max Activating Token Index: 980