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

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

Neuron 621 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5807. Min Act: -0.0001

Data Index: 324145 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5311. Min Act: -0.0001

Data Index: 689496 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5433. Min Act: -0.0001

Data Index: 1043303 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5892. Min Act: -0.0001

Data Index: 1256839 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5207. Min Act: -0.0001

Data Index: 738761 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4418. Min Act: -0.0001

Data Index: 558592 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4703. Min Act: -0.0001

Data Index: 599134 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4680. Min Act: -0.0001

Data Index: 1078312 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4953. Min Act: -0.0001

Data Index: 602931 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4706. Min Act: -0.0001

Data Index: 80476 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4683. Min Act: -0.0001

Data Index: 1172422 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4563. Min Act: -0.0001

Data Index: 877066 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4574. Min Act: -0.0001

Data Index: 1008203 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4537. Min Act: -0.0001

Data Index: 586331 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4539. Min Act: -0.0001

Data Index: 1257825 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4370. Min Act: -0.0001

Data Index: 1033374 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4481. Min Act: -0.0001

Data Index: 489525 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4384. Min Act: -0.0001

Data Index: 170837 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4510. Min Act: -0.0001

Data Index: 1095162 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4608. Min Act: -0.0001

Data Index: 982728 (C4 (Web Text))

Max Activating Token Index: 795