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

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

Neuron 104 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4862. Min Act: -0.0001

Data Index: 1177112 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4850. Min Act: -0.0001

Data Index: 374901 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4157. Min Act: -0.0000

Data Index: 179488 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4230. Min Act: -0.0001

Data Index: 166842 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4117. Min Act: -0.0000

Data Index: 534689 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3790. Min Act: -0.0001

Data Index: 1052697 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3925. Min Act: -0.0001

Data Index: 1127659 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3922. Min Act: -0.0001

Data Index: 952718 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3901. Min Act: -0.0000

Data Index: 224062 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3641. Min Act: -0.0000

Data Index: 817624 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3524. Min Act: -0.0000

Data Index: 51559 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1187916 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1240114 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1091702 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3374. Min Act: -0.0001

Data Index: 177901 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3422. Min Act: -0.0001

Data Index: 1037814 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3199. Min Act: -0.0001

Data Index: 858090 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3502. Min Act: -0.0001

Data Index: 210771 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3135. Min Act: -0.0001

Data Index: 432168 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3122. Min Act: -0.0000

Data Index: 801155 (C4 (Web Text))

Max Activating Token Index: 574