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

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

Neuron 1090 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5789. Min Range: -6.5789

Max Act: 6.5789. Min Act: -0.0000

Data Index: 1099920 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 6.5789. Min Range: -6.5789

Max Act: 6.1602. Min Act: -0.0000

Data Index: 1089976 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 6.5789. Min Range: -6.5789

Max Act: 6.1187. Min Act: -0.0000

Data Index: 1220548 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 6.5789. Min Range: -6.5789

Max Act: 6.0829. Min Act: -0.0000

Data Index: 1223635 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 6.5789. Min Range: -6.5789

Max Act: 6.2415. Min Act: -0.0000

Data Index: 922679 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 6.5789. Min Range: -6.5789

Max Act: 6.0563. Min Act: -0.0000

Data Index: 1045869 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 6.5789. Min Range: -6.5789

Max Act: 5.9769. Min Act: -0.0000

Data Index: 541150 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 6.5789. Min Range: -6.5789

Max Act: 5.5872. Min Act: -0.0000

Data Index: 280088 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 6.5789. Min Range: -6.5789

Max Act: 5.6056. Min Act: -0.0000

Data Index: 652976 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 6.5789. Min Range: -6.5789

Max Act: 5.4873. Min Act: -0.0000

Data Index: 506005 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 6.5789. Min Range: -6.5789

Max Act: 5.4479. Min Act: -0.0000

Data Index: 203096 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 6.5789. Min Range: -6.5789

Max Act: 4.9892. Min Act: -0.0000

Data Index: 1085209 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 6.5789. Min Range: -6.5789

Max Act: 4.9151. Min Act: -0.0000

Data Index: 289413 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 6.5789. Min Range: -6.5789

Max Act: 5.2421. Min Act: -0.0000

Data Index: 228816 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 6.5789. Min Range: -6.5789

Max Act: 5.3674. Min Act: -0.0000

Data Index: 545592 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 6.5789. Min Range: -6.5789

Max Act: 5.1814. Min Act: -0.0000

Data Index: 384116 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 6.5789. Min Range: -6.5789

Max Act: 5.1659. Min Act: -0.0000

Data Index: 456516 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 6.5789. Min Range: -6.5789

Max Act: 4.9913. Min Act: -0.0000

Data Index: 343876 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 6.5789. Min Range: -6.5789

Max Act: 5.1042. Min Act: -0.0000

Data Index: 555850 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 6.5789. Min Range: -6.5789

Max Act: 5.1108. Min Act: -0.0000

Data Index: 504205 (C4 (Web Text))

Max Activating Token Index: 228