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

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

Neuron 810 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3460. Min Act: -0.0000

Data Index: 956632 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3438. Min Act: -0.0000

Data Index: 192963 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3236. Min Act: -0.0000

Data Index: 514459 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2928. Min Act: -0.0000

Data Index: 971107 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2787. Min Act: -0.0000

Data Index: 643143 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2940. Min Act: -0.0000

Data Index: 1075193 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2672. Min Act: -0.0000

Data Index: 757821 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2633. Min Act: -0.0000

Data Index: 198226 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2212. Min Act: -0.0000

Data Index: 623553 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2188. Min Act: -0.0000

Data Index: 983285 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.1966. Min Act: -0.0000

Data Index: 948285 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.1958. Min Act: -0.0000

Data Index: 553015 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2163. Min Act: -0.0000

Data Index: 285225 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1173086 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2084. Min Act: -0.0000

Data Index: 485559 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.1888. Min Act: -0.0001

Data Index: 757955 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.1986. Min Act: -0.0000

Data Index: 214371 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1332899 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.1896. Min Act: -0.0000

Data Index: 621419 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1121523 (C4 (Web Text))

Max Activating Token Index: 424