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

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

Neuron 4987 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: 0.7670. Min Range: -0.7670

Max Act: 0.7474. Min Act: -0.0000

Data Index: 518869 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.7669. Min Act: -0.0000

Data Index: 912880 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1318361 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.7258. Min Act: -0.0000

Data Index: 459402 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6830. Min Act: -0.0000

Data Index: 773649 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6586. Min Act: -0.0000

Data Index: 577717 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6805. Min Act: -0.0000

Data Index: 160071 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6879. Min Act: -0.0000

Data Index: 471264 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1276664 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1063655 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1125280 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6420. Min Act: -0.0000

Data Index: 371128 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6034. Min Act: -0.0000

Data Index: 648445 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6533. Min Act: -0.0000

Data Index: 973314 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6132. Min Act: -0.0000

Data Index: 314273 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1243491 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6056. Min Act: -0.0000

Data Index: 775976 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5793. Min Act: -0.0000

Data Index: 46491 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6102. Min Act: -0.0000

Data Index: 289237 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5888. Min Act: -0.0000

Data Index: 148864 (C4 (Web Text))

Max Activating Token Index: 341