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

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

Neuron 44 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.2845. Min Act: -0.0000

Data Index: 1024057 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.0128. Min Act: -0.0000

Data Index: 1275407 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.9573. Min Act: -0.0000

Data Index: 656339 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1433780 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.8842. Min Act: -0.0000

Data Index: 675307 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.9558. Min Act: -0.0000

Data Index: 21726 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.8349. Min Act: -0.0000

Data Index: 234411 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1292582 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.8803. Min Act: -0.0000

Data Index: 120069 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1229776 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1344756 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1516598 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.7815. Min Act: -0.0000

Data Index: 539781 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1173526 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.9282. Min Act: -0.0000

Data Index: 822297 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.9165. Min Act: -0.0000

Data Index: 117087 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.8330. Min Act: -0.0000

Data Index: 718744 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1564167 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.9145. Min Act: -0.0000

Data Index: 825330 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.8336. Min Act: -0.0000

Data Index: 791473 (C4 (Web Text))

Max Activating Token Index: 824