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

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

Neuron 2574 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.9210. Min Act: -0.0000

Data Index: 1510693 (Python Code)

Max Activating Token Index: 967

Text #1

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.7444. Min Act: -0.0000

Data Index: 780557 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.5313. Min Act: -0.0000

Data Index: 1454073 (Python Code)

Max Activating Token Index: 889

Text #3

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.6608. Min Act: -0.0000

Data Index: 1540291 (Python Code)

Max Activating Token Index: 116

Text #4

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.4894. Min Act: -0.0000

Data Index: 1178883 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.6272. Min Act: -0.0000

Data Index: 377404 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.6166. Min Act: -0.0000

Data Index: 1586204 (Python Code)

Max Activating Token Index: 401

Text #7

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.3158. Min Act: -0.0000

Data Index: 1533370 (Python Code)

Max Activating Token Index: 748

Text #8

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.5679. Min Act: -0.0000

Data Index: 1019609 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.2987. Min Act: -0.0000

Data Index: 1468984 (Python Code)

Max Activating Token Index: 854

Text #10

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.3752. Min Act: -0.0000

Data Index: 1387041 (Python Code)

Max Activating Token Index: 981

Text #11

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.2634. Min Act: -0.0000

Data Index: 1540233 (Python Code)

Max Activating Token Index: 923

Text #12

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.3491. Min Act: -0.0000

Data Index: 1114686 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.3332. Min Act: -0.0000

Data Index: 812821 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.2777. Min Act: -0.0000

Data Index: 1355947 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.4331. Min Act: -0.0000

Data Index: 1107648 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.2621. Min Act: -0.0000

Data Index: 1484186 (Python Code)

Max Activating Token Index: 91

Text #17

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.1510. Min Act: -0.0000

Data Index: 1519800 (Python Code)

Max Activating Token Index: 973

Text #18

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.1363. Min Act: -0.0000

Data Index: 334027 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.2385. Min Act: -0.0000

Data Index: 1071623 (C4 (Web Text))

Max Activating Token Index: 473