Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1130 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0986. Min Range: -2.0986

Max Act: 2.0986. Min Act: -0.0000

Data Index: 242701 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.8873. Min Act: -0.0000

Data Index: 1213967 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.8274. Min Act: -0.0000

Data Index: 224757 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.7696. Min Act: -0.0000

Data Index: 490378 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.7098. Min Act: -0.0000

Data Index: 1274790 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.6870. Min Act: -0.0000

Data Index: 42341 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.6727. Min Act: -0.0000

Data Index: 102326 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.7606. Min Act: -0.0000

Data Index: 684693 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.6531. Min Act: -0.0000

Data Index: 462557 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.6219. Min Act: -0.0000

Data Index: 688497 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.6155. Min Act: -0.0000

Data Index: 556638 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.6761. Min Act: -0.0000

Data Index: 212293 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.5794. Min Act: -0.0000

Data Index: 1097522 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.5678. Min Act: -0.0000

Data Index: 321400 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.4740. Min Act: -0.0000

Data Index: 620635 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.4607. Min Act: -0.0000

Data Index: 95257 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.4514. Min Act: -0.0000

Data Index: 411378 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.5395. Min Act: -0.0000

Data Index: 1077456 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.6136. Min Act: -0.0000

Data Index: 1256531 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 2.0986. Min Range: -2.0986

Max Act: 1.4754. Min Act: -0.0000

Data Index: 1306172 (C4 (Web Text))

Max Activating Token Index: 789