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

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

Neuron 4000 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: 0.1123. Min Range: -0.1123

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1023518 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0863. Min Act: -0.0001

Data Index: 728215 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0830. Min Act: -0.0001

Data Index: 787722 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0781. Min Act: -0.0001

Data Index: 432633 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0677. Min Act: -0.0001

Data Index: 577408 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1345017 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0659. Min Act: -0.0001

Data Index: 860654 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0651. Min Act: -0.0001

Data Index: 425218 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1036572 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0648. Min Act: -0.0001

Data Index: 226384 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0639. Min Act: -0.0001

Data Index: 591363 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0641. Min Act: -0.0001

Data Index: 885173 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1289370 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0652. Min Act: -0.0001

Data Index: 715082 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0627. Min Act: -0.0001

Data Index: 250940 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1194007 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0553. Min Act: -0.0001

Data Index: 1132224 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1134174 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0593. Min Act: -0.0001

Data Index: 690391 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0571. Min Act: -0.0001

Data Index: 609846 (C4 (Web Text))

Max Activating Token Index: 949