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

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

Neuron 892 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.7950. Min Act: -0.0000

Data Index: 275375 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.4287. Min Act: -0.0000

Data Index: 33223 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.2411. Min Act: -0.0000

Data Index: 964992 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.2724. Min Act: -0.0000

Data Index: 445930 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.1619. Min Act: -0.0000

Data Index: 457750 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.1658. Min Act: -0.0000

Data Index: 616802 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1176795 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.2650. Min Act: -0.0000

Data Index: 808271 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.0799. Min Act: -0.0000

Data Index: 620323 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.0199. Min Act: -0.0000

Data Index: 837335 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.0463. Min Act: -0.0000

Data Index: 418482 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.0917. Min Act: -0.0000

Data Index: 1062395 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.0586. Min Act: -0.0000

Data Index: 396298 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 1.7950. Min Range: -1.7950

Max Act: 0.9496. Min Act: -0.0000

Data Index: 298794 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 1.7950. Min Range: -1.7950

Max Act: 0.9915. Min Act: -0.0000

Data Index: 921162 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.0379. Min Act: -0.0000

Data Index: 189360 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 1.7950. Min Range: -1.7950

Max Act: 0.9654. Min Act: -0.0000

Data Index: 1245917 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 1.7950. Min Range: -1.7950

Max Act: 1.0251. Min Act: -0.0000

Data Index: 1093050 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.7950. Min Range: -1.7950

Max Act: 0.9793. Min Act: -0.0000

Data Index: 857308 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 1.7950. Min Range: -1.7950

Max Act: 0.9853. Min Act: -0.0000

Data Index: 51461 (C4 (Web Text))

Max Activating Token Index: 371