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

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

Neuron 3108 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: 3.0961. Min Range: -3.0961

Max Act: 3.0961. Min Act: -0.0000

Data Index: 1230984 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 3.0961. Min Range: -3.0961

Max Act: 2.6969. Min Act: -0.0000

Data Index: 512935 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 3.0961. Min Range: -3.0961

Max Act: 2.5870. Min Act: -0.0000

Data Index: 613269 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 3.0961. Min Range: -3.0961

Max Act: 2.0285. Min Act: -0.0000

Data Index: 767385 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 3.0961. Min Range: -3.0961

Max Act: 2.0274. Min Act: -0.0000

Data Index: 1268945 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 3.0961. Min Range: -3.0961

Max Act: 2.0009. Min Act: -0.0000

Data Index: 1199375 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 3.0961. Min Range: -3.0961

Max Act: 2.0493. Min Act: -0.0000

Data Index: 810636 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 3.0961. Min Range: -3.0961

Max Act: 1.7346. Min Act: -0.0000

Data Index: 898844 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 3.0961. Min Range: -3.0961

Max Act: 1.6869. Min Act: -0.0000

Data Index: 260566 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 3.0961. Min Range: -3.0961

Max Act: 1.6907. Min Act: -0.0000

Data Index: 298035 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 3.0961. Min Range: -3.0961

Max Act: 1.7516. Min Act: -0.0000

Data Index: 923014 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 3.0961. Min Range: -3.0961

Max Act: 1.7109. Min Act: -0.0000

Data Index: 513555 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 3.0961. Min Range: -3.0961

Max Act: 1.6486. Min Act: -0.0000

Data Index: 1310411 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 3.0961. Min Range: -3.0961

Max Act: 1.6212. Min Act: -0.0000

Data Index: 768626 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 3.0961. Min Range: -3.0961

Max Act: 1.6116. Min Act: -0.0000

Data Index: 801905 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 3.0961. Min Range: -3.0961

Max Act: 1.5727. Min Act: -0.0000

Data Index: 1188153 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 3.0961. Min Range: -3.0961

Max Act: 1.6521. Min Act: -0.0000

Data Index: 1077100 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 3.0961. Min Range: -3.0961

Max Act: 1.5377. Min Act: -0.0000

Data Index: 468898 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 3.0961. Min Range: -3.0961

Max Act: 1.4427. Min Act: -0.0000

Data Index: 244570 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 3.0961. Min Range: -3.0961

Max Act: 1.4464. Min Act: -0.0000

Data Index: 544173 (C4 (Web Text))

Max Activating Token Index: 338