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

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

Neuron 416 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.6534. Min Act: -0.0001

Data Index: 516178 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.6659. Min Act: -0.0000

Data Index: 417778 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.6341. Min Act: -0.0000

Data Index: 584694 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.6472. Min Act: -0.0000

Data Index: 141775 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.6400. Min Act: -0.0000

Data Index: 500955 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.6397. Min Act: -0.0000

Data Index: 240859 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1007719 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.6444. Min Act: -0.0000

Data Index: 36136 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1065944 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1046340 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.6002. Min Act: -0.0000

Data Index: 756654 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5997. Min Act: -0.0000

Data Index: 357637 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.6053. Min Act: -0.0001

Data Index: 903961 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5898. Min Act: -0.0000

Data Index: 65931 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1129519 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5863. Min Act: -0.0000

Data Index: 784331 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5647. Min Act: -0.0000

Data Index: 940070 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5821. Min Act: -0.0000

Data Index: 639631 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1161740 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1118455 (C4 (Web Text))

Max Activating Token Index: 876