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

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

Neuron 4896 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: 2.0063. Min Range: -2.0063

Max Act: 2.0063. Min Act: -0.0000

Data Index: 295822 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.8078. Min Act: -0.0000

Data Index: 1063056 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.7104. Min Act: -0.0000

Data Index: 1143422 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.8037. Min Act: -0.0000

Data Index: 298247 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.6528. Min Act: -0.0000

Data Index: 637323 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.7043. Min Act: -0.0000

Data Index: 433576 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.5605. Min Act: -0.0000

Data Index: 441982 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.6155. Min Act: -0.0000

Data Index: 219145 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.5251. Min Act: -0.0000

Data Index: 652633 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.5836. Min Act: -0.0000

Data Index: 643909 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.4836. Min Act: -0.0000

Data Index: 1293842 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.4683. Min Act: -0.0000

Data Index: 234481 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.3792. Min Act: -0.0000

Data Index: 294021 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.3411. Min Act: -0.0000

Data Index: 1566060 (Python Code)

Max Activating Token Index: 349

Text #14

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.3771. Min Act: -0.0000

Data Index: 466154 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.4583. Min Act: -0.0001

Data Index: 1577301 (Python Code)

Max Activating Token Index: 186

Text #16

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.3618. Min Act: -0.0000

Data Index: 513559 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.3301. Min Act: -0.0000

Data Index: 133720 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.1821. Min Act: -0.0000

Data Index: 1091886 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 2.0063. Min Range: -2.0063

Max Act: 1.1656. Min Act: -0.0000

Data Index: 839832 (C4 (Web Text))

Max Activating Token Index: 704