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

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

Neuron 3162 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: 0.0489. Min Range: -0.0489

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1474990 (Python Code)

Max Activating Token Index: 753

Text #1

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0462. Min Act: -0.0001

Data Index: 888432 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0470. Min Act: -0.0001

Data Index: 553980 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0445. Min Act: -0.0001

Data Index: 1309614 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0471. Min Act: -0.0001

Data Index: 643965 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0453. Min Act: -0.0001

Data Index: 872877 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1186226 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0443. Min Act: -0.0001

Data Index: 481378 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0440. Min Act: -0.0001

Data Index: 723659 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0442. Min Act: -0.0001

Data Index: 1242596 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0438. Min Act: -0.0001

Data Index: 1132216 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0434. Min Act: -0.0001

Data Index: 808473 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1149617 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1184149 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0416. Min Act: -0.0001

Data Index: 2687 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0445. Min Act: -0.0001

Data Index: 391454 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0430. Min Act: -0.0001

Data Index: 146373 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1644515 (Python Code)

Max Activating Token Index: 812

Text #18

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0441. Min Act: -0.0001

Data Index: 719423 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0410. Min Act: -0.0001

Data Index: 369232 (C4 (Web Text))

Max Activating Token Index: 885