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

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

Neuron 901 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2644. Min Range: -1.2644

Max Act: 1.2644. Min Act: -0.0000

Data Index: 353261 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 1.2644. Min Range: -1.2644

Max Act: 1.0901. Min Act: -0.0000

Data Index: 1326445 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.9811. Min Act: -0.0000

Data Index: 723140 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.9463. Min Act: -0.0000

Data Index: 852612 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1154622 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.9540. Min Act: -0.0000

Data Index: 47575 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.9516. Min Act: -0.0000

Data Index: 603219 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.9382. Min Act: -0.0000

Data Index: 728475 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.9671. Min Act: -0.0000

Data Index: 360564 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.9097. Min Act: -0.0000

Data Index: 1331094 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.8910. Min Act: -0.0000

Data Index: 641737 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.8510. Min Act: -0.0000

Data Index: 856116 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1339603 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.8706. Min Act: -0.0000

Data Index: 933639 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1146355 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.8609. Min Act: -0.0000

Data Index: 897128 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.8470. Min Act: -0.0000

Data Index: 994635 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1359638 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1063918 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 1.2644. Min Range: -1.2644

Max Act: 0.7785. Min Act: -0.0000

Data Index: 711795 (C4 (Web Text))

Max Activating Token Index: 762