Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3733 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.7575. Min Act: -0.0001

Data Index: 1295373 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5148. Min Act: -0.0001

Data Index: 566497 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4966. Min Act: -0.0001

Data Index: 319584 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5260. Min Act: -0.0001

Data Index: 325223 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4725. Min Act: -0.0001

Data Index: 795397 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4465. Min Act: -0.0001

Data Index: 1288003 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4979. Min Act: -0.0001

Data Index: 967099 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5006. Min Act: -0.0001

Data Index: 1343924 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4424. Min Act: -0.0001

Data Index: 382726 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4755. Min Act: -0.0001

Data Index: 1043735 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4180. Min Act: -0.0001

Data Index: 571867 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4571. Min Act: -0.0001

Data Index: 278051 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4442. Min Act: -0.0001

Data Index: 1232648 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4150. Min Act: -0.0001

Data Index: 1355138 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4253. Min Act: -0.0001

Data Index: 119185 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4216. Min Act: -0.0001

Data Index: 884229 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4080. Min Act: -0.0001

Data Index: 510061 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4082. Min Act: -0.0001

Data Index: 720998 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.3941. Min Act: -0.0001

Data Index: 444670 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.4066. Min Act: -0.0001

Data Index: 193720 (C4 (Web Text))

Max Activating Token Index: 507