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

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

Neuron 639 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5061. Min Range: -2.5061

Max Act: 2.5061. Min Act: 0.0000

Data Index: 996023 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 2.5061. Min Range: -2.5061

Max Act: 2.3319. Min Act: -0.0000

Data Index: 289470 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 2.5061. Min Range: -2.5061

Max Act: 2.1169. Min Act: -0.0000

Data Index: 451179 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.9953. Min Act: -0.0000

Data Index: 1080807 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 2.5061. Min Range: -2.5061

Max Act: 2.0570. Min Act: -0.0000

Data Index: 943970 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.8001. Min Act: -0.0000

Data Index: 1244672 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.7922. Min Act: -0.0000

Data Index: 1305777 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.7846. Min Act: -0.0000

Data Index: 792424 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.7575. Min Act: -0.0000

Data Index: 1296347 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.7515. Min Act: -0.0000

Data Index: 306368 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.7386. Min Act: -0.0000

Data Index: 120955 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.7947. Min Act: 0.0000

Data Index: 917788 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.7005. Min Act: -0.0000

Data Index: 1359634 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.6970. Min Act: -0.0000

Data Index: 1283962 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.6591. Min Act: -0.0000

Data Index: 1180402 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.6337. Min Act: -0.0000

Data Index: 746127 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.7299. Min Act: -0.0000

Data Index: 11316 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.6864. Min Act: -0.0000

Data Index: 868572 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.5050. Min Act: -0.0000

Data Index: 353781 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 2.5061. Min Range: -2.5061

Max Act: 1.5825. Min Act: -0.0000

Data Index: 1194272 (C4 (Web Text))

Max Activating Token Index: 147