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

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

Neuron 550 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1320303 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1272478 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.7436. Min Act: -0.0001

Data Index: 381934 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6588. Min Act: -0.0001

Data Index: 907717 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6712. Min Act: -0.0001

Data Index: 324307 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6470. Min Act: -0.0001

Data Index: 238671 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6616. Min Act: -0.0001

Data Index: 1156332 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.7083. Min Act: -0.0001

Data Index: 448570 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6963. Min Act: -0.0001

Data Index: 785511 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6555. Min Act: -0.0001

Data Index: 154299 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.5881. Min Act: -0.0001

Data Index: 388194 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6028. Min Act: -0.0001

Data Index: 772919 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6794. Min Act: -0.0001

Data Index: 464774 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.5843. Min Act: -0.0001

Data Index: 412035 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6142. Min Act: -0.0001

Data Index: 814630 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6521. Min Act: -0.0001

Data Index: 867653 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6656. Min Act: -0.0001

Data Index: 669088 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.5592. Min Act: -0.0001

Data Index: 941254 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.5954. Min Act: -0.0001

Data Index: 1272094 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.5924. Min Act: -0.0001

Data Index: 979794 (C4 (Web Text))

Max Activating Token Index: 918