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

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

Neuron 2582 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.7220. Min Act: -0.0000

Data Index: 320982 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.5587. Min Act: -0.0001

Data Index: 671892 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.5591. Min Act: -0.0001

Data Index: 533419 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.5445. Min Act: -0.0000

Data Index: 360290 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.5284. Min Act: -0.0001

Data Index: 282973 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.5216. Min Act: -0.0000

Data Index: 554478 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.5090. Min Act: -0.0000

Data Index: 804300 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4586. Min Act: -0.0000

Data Index: 1073999 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1048375 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1095135 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4593. Min Act: -0.0000

Data Index: 7265 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1214686 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4566. Min Act: -0.0000

Data Index: 114266 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4729. Min Act: -0.0000

Data Index: 712003 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4570. Min Act: -0.0000

Data Index: 66489 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1242621 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4540. Min Act: -0.0000

Data Index: 371924 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4681. Min Act: -0.0000

Data Index: 509181 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4645. Min Act: -0.0000

Data Index: 707279 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.7220. Min Range: -0.7220

Max Act: 0.4467. Min Act: -0.0000

Data Index: 752432 (C4 (Web Text))

Max Activating Token Index: 261