Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 404 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.6584. Min Act: -0.0000

Data Index: 446757 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.2519. Min Act: -0.0000

Data Index: 659098 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.1051. Min Act: -0.0000

Data Index: 322996 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.1770. Min Act: -0.0000

Data Index: 598214 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1329750 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1223 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.9152. Min Act: -0.0000

Data Index: 884582 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.8520. Min Act: -0.0000

Data Index: 108590 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.8747. Min Act: -0.0000

Data Index: 400663 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.8545. Min Act: -0.0000

Data Index: 1086573 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.8810. Min Act: -0.0000

Data Index: 855638 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1132940 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.8120. Min Act: -0.0000

Data Index: 516962 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1006024 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1073262 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.7856. Min Act: -0.0000

Data Index: 976088 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.8807. Min Act: -0.0000

Data Index: 210339 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.8161. Min Act: -0.0000

Data Index: 541526 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.7355. Min Act: -0.0000

Data Index: 701311 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 1.6584. Min Range: -1.6584

Max Act: 0.7495. Min Act: -0.0000

Data Index: 180412 (C4 (Web Text))

Max Activating Token Index: 39