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

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

Neuron 4855 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0827. Min Range: -1.0827

Max Act: 1.0012. Min Act: -0.0000

Data Index: 354589 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 1.0827. Min Range: -1.0827

Max Act: 1.0639. Min Act: -0.0000

Data Index: 1225276 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 1.0827. Min Range: -1.0827

Max Act: 1.0084. Min Act: -0.0000

Data Index: 312574 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 1.0827. Min Range: -1.0827

Max Act: 1.0827. Min Act: -0.0000

Data Index: 1254400 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.8807. Min Act: -0.0000

Data Index: 677438 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9831. Min Act: -0.0000

Data Index: 195539 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9740. Min Act: -0.0000

Data Index: 668171 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9729. Min Act: -0.0000

Data Index: 455549 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 1.0827. Min Range: -1.0827

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1254210 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 1.0827. Min Range: -1.0827

Max Act: 1.0098. Min Act: -0.0000

Data Index: 793560 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 1.0827. Min Range: -1.0827

Max Act: 1.0581. Min Act: -0.0000

Data Index: 29898 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9554. Min Act: -0.0000

Data Index: 268485 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1354619 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1317720 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9227. Min Act: -0.0000

Data Index: 81816 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.8477. Min Act: -0.0000

Data Index: 222014 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.8399. Min Act: -0.0000

Data Index: 111166 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.8525. Min Act: -0.0000

Data Index: 130235 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.8270. Min Act: -0.0000

Data Index: 92982 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.8715. Min Act: -0.0000

Data Index: 1178788 (C4 (Web Text))

Max Activating Token Index: 626