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

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

Neuron 2691 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: 0.8284. Min Range: -0.8284

Max Act: 0.8284. Min Act: -0.0001

Data Index: 157475 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.8034. Min Act: -0.0001

Data Index: 1090851 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.8145. Min Act: -0.0001

Data Index: 553070 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.8030. Min Act: -0.0001

Data Index: 1044241 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7902. Min Act: -0.0001

Data Index: 357733 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7555. Min Act: -0.0001

Data Index: 322392 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7792. Min Act: -0.0001

Data Index: 755293 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7487. Min Act: -0.0001

Data Index: 1093230 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7443. Min Act: -0.0001

Data Index: 1129592 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.8138. Min Act: -0.0001

Data Index: 1043693 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7195. Min Act: -0.0001

Data Index: 638491 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7848. Min Act: -0.0001

Data Index: 669870 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7469. Min Act: -0.0001

Data Index: 818551 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7236. Min Act: -0.0001

Data Index: 524105 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7478. Min Act: -0.0001

Data Index: 388353 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7431. Min Act: -0.0001

Data Index: 15853 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7190. Min Act: -0.0001

Data Index: 652572 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6970. Min Act: -0.0001

Data Index: 416337 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7395. Min Act: -0.0001

Data Index: 1007469 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7216. Min Act: -0.0001

Data Index: 613946 (C4 (Web Text))

Max Activating Token Index: 281