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

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

Neuron 1775 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: 0.7135. Min Range: -0.7135

Max Act: 0.7135. Min Act: -0.0000

Data Index: 683387 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1182999 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5813. Min Act: -0.0000

Data Index: 825759 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.6114. Min Act: -0.0000

Data Index: 1236377 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1227119 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.6106. Min Act: -0.0000

Data Index: 819143 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5876. Min Act: -0.0000

Data Index: 451853 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5317. Min Act: -0.0000

Data Index: 596005 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1282496 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1218479 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5335. Min Act: -0.0000

Data Index: 412257 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5287. Min Act: -0.0000

Data Index: 577760 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5210. Min Act: -0.0000

Data Index: 71868 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5320. Min Act: -0.0000

Data Index: 62721 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5422. Min Act: -0.0000

Data Index: 251818 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5397. Min Act: -0.0000

Data Index: 10823 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5185. Min Act: -0.0000

Data Index: 448009 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.4926. Min Act: -0.0000

Data Index: 681299 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1184633 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.4845. Min Act: -0.0000

Data Index: 553867 (C4 (Web Text))

Max Activating Token Index: 943