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

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

Neuron 954 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.9037. Min Act: -0.0000

Data Index: 929541 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.8966. Min Act: -0.0000

Data Index: 456361 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.8369. Min Act: -0.0000

Data Index: 422111 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7716. Min Act: -0.0000

Data Index: 559699 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1104024 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7497. Min Act: -0.0000

Data Index: 120987 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7337. Min Act: -0.0000

Data Index: 567874 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1078484 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7112. Min Act: -0.0000

Data Index: 197666 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6921. Min Act: -0.0000

Data Index: 130509 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6912. Min Act: -0.0000

Data Index: 827081 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1292580 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6821. Min Act: -0.0000

Data Index: 370233 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6670. Min Act: -0.0000

Data Index: 790536 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6835. Min Act: -0.0000

Data Index: 826137 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6522. Min Act: -0.0000

Data Index: 786768 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6327. Min Act: -0.0000

Data Index: 955113 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6729. Min Act: -0.0000

Data Index: 72565 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6610. Min Act: -0.0000

Data Index: 213059 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6757. Min Act: -0.0000

Data Index: 48215 (C4 (Web Text))

Max Activating Token Index: 185