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

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

Neuron 813 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: 5.0579. Min Range: -5.0579

Max Act: 5.0579. Min Act: -0.0001

Data Index: 1009138 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 5.0579. Min Range: -5.0579

Max Act: 4.4803. Min Act: -0.0001

Data Index: 586418 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.8035. Min Act: -0.0001

Data Index: 571305 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.8155. Min Act: -0.0001

Data Index: 358512 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.7249. Min Act: -0.0001

Data Index: 771444 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.5070. Min Act: -0.0001

Data Index: 236461 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.6278. Min Act: -0.0001

Data Index: 405666 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.5913. Min Act: -0.0000

Data Index: 823486 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.2349. Min Act: -0.0001

Data Index: 173817 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.4659. Min Act: -0.0001

Data Index: 114516 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.4605. Min Act: -0.0001

Data Index: 202274 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.4415. Min Act: -0.0001

Data Index: 1210672 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.5533. Min Act: -0.0001

Data Index: 942979 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.1458. Min Act: -0.0001

Data Index: 1017407 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.1438. Min Act: -0.0001

Data Index: 879322 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.7074. Min Act: -0.0001

Data Index: 1079761 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.3753. Min Act: -0.0001

Data Index: 531948 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.3486. Min Act: -0.0001

Data Index: 986888 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.5389. Min Act: -0.0001

Data Index: 365291 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 5.0579. Min Range: -5.0579

Max Act: 3.3338. Min Act: -0.0001

Data Index: 871576 (C4 (Web Text))

Max Activating Token Index: 197