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

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

Neuron 1337 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3351. Min Range: -2.3351

Max Act: 2.3351. Min Act: -0.0000

Data Index: 459713 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 2.3351. Min Range: -2.3351

Max Act: 2.3073. Min Act: -0.0000

Data Index: 128846 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 2.3351. Min Range: -2.3351

Max Act: 2.2526. Min Act: -0.0000

Data Index: 119647 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 2.3351. Min Range: -2.3351

Max Act: 2.2190. Min Act: -0.0000

Data Index: 1033660 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 2.3351. Min Range: -2.3351

Max Act: 2.2054. Min Act: -0.0000

Data Index: 612667 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.9576. Min Act: -0.0000

Data Index: 768911 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.9514. Min Act: -0.0000

Data Index: 926668 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.8499. Min Act: -0.0000

Data Index: 41634 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.8467. Min Act: -0.0000

Data Index: 802585 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.8743. Min Act: -0.0000

Data Index: 1091567 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.7567. Min Act: -0.0000

Data Index: 616312 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.7211. Min Act: -0.0000

Data Index: 218974 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.7158. Min Act: -0.0000

Data Index: 974140 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.6722. Min Act: -0.0000

Data Index: 770478 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.6821. Min Act: -0.0000

Data Index: 236401 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.6748. Min Act: -0.0000

Data Index: 925359 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.6648. Min Act: -0.0000

Data Index: 1072682 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.6492. Min Act: -0.0000

Data Index: 307125 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.7301. Min Act: -0.0000

Data Index: 475243 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.6316. Min Act: -0.0000

Data Index: 227000 (C4 (Web Text))

Max Activating Token Index: 924