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

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

Neuron 2647 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: 0.6670. Min Range: -0.6670

Max Act: 0.6670. Min Act: -0.0001

Data Index: 1149270 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.6478. Min Act: -0.0001

Data Index: 33564 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5814. Min Act: -0.0001

Data Index: 1080407 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5634. Min Act: -0.0001

Data Index: 590201 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5578. Min Act: -0.0001

Data Index: 605130 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5186. Min Act: -0.0001

Data Index: 453892 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5228. Min Act: -0.0001

Data Index: 816586 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5362. Min Act: -0.0001

Data Index: 388819 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4924. Min Act: -0.0001

Data Index: 383 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5216. Min Act: -0.0001

Data Index: 104813 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4525. Min Act: -0.0001

Data Index: 465327 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4803. Min Act: -0.0001

Data Index: 733563 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4919. Min Act: -0.0001

Data Index: 650483 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4555. Min Act: -0.0001

Data Index: 894420 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4678. Min Act: -0.0001

Data Index: 771364 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4701. Min Act: -0.0001

Data Index: 652087 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4614. Min Act: -0.0001

Data Index: 837596 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4612. Min Act: -0.0001

Data Index: 769153 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.3734. Min Act: -0.0001

Data Index: 784360 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4576. Min Act: -0.0001

Data Index: 775827 (C4 (Web Text))

Max Activating Token Index: 1002