Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 145 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.5600. Min Act: -0.0001

Data Index: 26925 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.5271. Min Act: -0.0000

Data Index: 705282 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.5243. Min Act: -0.0001

Data Index: 395526 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4879. Min Act: -0.0001

Data Index: 977875 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4811. Min Act: -0.0001

Data Index: 751216 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4826. Min Act: -0.0001

Data Index: 369298 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4957. Min Act: -0.0000

Data Index: 124551 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4781. Min Act: -0.0001

Data Index: 722166 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4463. Min Act: -0.0001

Data Index: 426852 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4727. Min Act: -0.0000

Data Index: 972069 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4903. Min Act: -0.0000

Data Index: 729571 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4628. Min Act: -0.0000

Data Index: 146398 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.3996. Min Act: -0.0001

Data Index: 1228123 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4370. Min Act: -0.0001

Data Index: 263606 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4345. Min Act: -0.0001

Data Index: 621036 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4290. Min Act: -0.0000

Data Index: 724984 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4009. Min Act: -0.0001

Data Index: 827250 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4076. Min Act: -0.0001

Data Index: 388394 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.3925. Min Act: -0.0000

Data Index: 940538 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.5600. Min Range: -0.5600

Max Act: 0.4040. Min Act: -0.0000

Data Index: 973782 (C4 (Web Text))

Max Activating Token Index: 345