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

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

Neuron 6064 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5897. Min Range: -3.5897

Max Act: 3.5897. Min Act: -0.0000

Data Index: 1300482 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 3.5897. Min Range: -3.5897

Max Act: 3.4659. Min Act: -0.0000

Data Index: 1253272 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 3.5897. Min Range: -3.5897

Max Act: 3.2435. Min Act: -0.0000

Data Index: 641223 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 3.5897. Min Range: -3.5897

Max Act: 3.0630. Min Act: -0.0000

Data Index: 1067730 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 3.5897. Min Range: -3.5897

Max Act: 3.0251. Min Act: -0.0000

Data Index: 1024247 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 3.5897. Min Range: -3.5897

Max Act: 2.6659. Min Act: -0.0000

Data Index: 289636 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 3.5897. Min Range: -3.5897

Max Act: 3.0635. Min Act: -0.0000

Data Index: 551567 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 3.5897. Min Range: -3.5897

Max Act: 2.7043. Min Act: -0.0000

Data Index: 399805 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 3.5897. Min Range: -3.5897

Max Act: 2.6916. Min Act: -0.0000

Data Index: 1061532 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 3.5897. Min Range: -3.5897

Max Act: 2.6865. Min Act: -0.0000

Data Index: 444439 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 3.5897. Min Range: -3.5897

Max Act: 2.6391. Min Act: -0.0000

Data Index: 8770 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 3.5897. Min Range: -3.5897

Max Act: 2.6235. Min Act: -0.0000

Data Index: 253934 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 3.5897. Min Range: -3.5897

Max Act: 2.6120. Min Act: -0.0000

Data Index: 153709 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 3.5897. Min Range: -3.5897

Max Act: 2.7426. Min Act: -0.0000

Data Index: 288107 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 3.5897. Min Range: -3.5897

Max Act: 2.4560. Min Act: -0.0000

Data Index: 162427 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 3.5897. Min Range: -3.5897

Max Act: 2.5339. Min Act: -0.0000

Data Index: 1000092 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 3.5897. Min Range: -3.5897

Max Act: 2.4024. Min Act: -0.0000

Data Index: 755981 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 3.5897. Min Range: -3.5897

Max Act: 2.3470. Min Act: -0.0000

Data Index: 568059 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 3.5897. Min Range: -3.5897

Max Act: 2.4071. Min Act: -0.0000

Data Index: 1183622 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 3.5897. Min Range: -3.5897

Max Act: 2.2801. Min Act: -0.0000

Data Index: 150035 (C4 (Web Text))

Max Activating Token Index: 759