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

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

Neuron 6063 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: 4.2337. Min Range: -4.2337

Max Act: 4.2337. Min Act: -0.0000

Data Index: 1033203 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.8848. Min Act: -0.0000

Data Index: 380087 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 4.2337. Min Range: -4.2337

Max Act: 4.0390. Min Act: -0.0000

Data Index: 769223 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.8908. Min Act: -0.0000

Data Index: 462237 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.7396. Min Act: -0.0000

Data Index: 304755 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.6647. Min Act: -0.0000

Data Index: 249510 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.4433. Min Act: -0.0000

Data Index: 1228805 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.7056. Min Act: -0.0000

Data Index: 559915 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.6678. Min Act: -0.0000

Data Index: 111378 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.4516. Min Act: -0.0000

Data Index: 865969 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.4842. Min Act: -0.0000

Data Index: 154378 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.3035. Min Act: -0.0000

Data Index: 1329994 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.2951. Min Act: -0.0000

Data Index: 765388 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.2301. Min Act: -0.0000

Data Index: 1015439 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 4.2337. Min Range: -4.2337

Max Act: 2.8690. Min Act: -0.0000

Data Index: 1309124 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.1271. Min Act: -0.0000

Data Index: 720225 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.1291. Min Act: -0.0000

Data Index: 968572 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 4.2337. Min Range: -4.2337

Max Act: 2.9523. Min Act: -0.0000

Data Index: 931333 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.0341. Min Act: -0.0000

Data Index: 967995 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 4.2337. Min Range: -4.2337

Max Act: 3.0519. Min Act: -0.0000

Data Index: 162864 (C4 (Web Text))

Max Activating Token Index: 264