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

Dataset: The Pile

Neuron 3875 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1769776 (The Pile)

Max Activating Token Index: 300

Text #1

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6691. Min Act: -0.0000

Data Index: 272337 (The Pile)

Max Activating Token Index: 710

Text #2

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1524671 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6474. Min Act: -0.0000

Data Index: 689229 (The Pile)

Max Activating Token Index: 864

Text #4

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1472536 (The Pile)

Max Activating Token Index: 209

Text #5

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1867400 (The Pile)

Max Activating Token Index: 923

Text #6

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6076. Min Act: -0.0000

Data Index: 909034 (The Pile)

Max Activating Token Index: 37

Text #7

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6416. Min Act: -0.0000

Data Index: 640660 (The Pile)

Max Activating Token Index: 847

Text #8

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5845. Min Act: -0.0000

Data Index: 511679 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6071. Min Act: -0.0000

Data Index: 181120 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6222. Min Act: -0.0000

Data Index: 461407 (The Pile)

Max Activating Token Index: 904

Text #11

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5966. Min Act: -0.0000

Data Index: 378757 (The Pile)

Max Activating Token Index: 77

Text #12

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5586. Min Act: -0.0000

Data Index: 666110 (The Pile)

Max Activating Token Index: 98

Text #13

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5575. Min Act: -0.0000

Data Index: 547662 (The Pile)

Max Activating Token Index: 75

Text #14

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6203. Min Act: -0.0000

Data Index: 586972 (The Pile)

Max Activating Token Index: 808

Text #15

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5768. Min Act: -0.0000

Data Index: 532270 (The Pile)

Max Activating Token Index: 770

Text #16

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5953. Min Act: -0.0000

Data Index: 213448 (The Pile)

Max Activating Token Index: 155

Text #17

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1595019 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5772. Min Act: -0.0000

Data Index: 540891 (The Pile)

Max Activating Token Index: 965

Text #19

Max Range: 0.7394. Min Range: -0.7394

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1217675 (The Pile)

Max Activating Token Index: 729