Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 108 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.8226. Min Range: -6.8226

Max Act: 6.8226. Min Act: -0.0000

Data Index: 912044 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 6.8226. Min Range: -6.8226

Max Act: 6.3563. Min Act: -0.0000

Data Index: 1165168 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 6.8226. Min Range: -6.8226

Max Act: 6.4941. Min Act: -0.0000

Data Index: 464303 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 6.8226. Min Range: -6.8226

Max Act: 6.0436. Min Act: -0.0000

Data Index: 405361 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 6.8226. Min Range: -6.8226

Max Act: 6.3294. Min Act: -0.0000

Data Index: 645095 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 6.8226. Min Range: -6.8226

Max Act: 6.6746. Min Act: -0.0000

Data Index: 605950 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 6.8226. Min Range: -6.8226

Max Act: 6.1154. Min Act: -0.0000

Data Index: 445819 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 6.8226. Min Range: -6.8226

Max Act: 6.4385. Min Act: -0.0000

Data Index: 792952 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 6.8226. Min Range: -6.8226

Max Act: 6.2999. Min Act: -0.0000

Data Index: 760833 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 6.8226. Min Range: -6.8226

Max Act: 6.2891. Min Act: -0.0000

Data Index: 80072 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 6.8226. Min Range: -6.8226

Max Act: 6.2521. Min Act: -0.0000

Data Index: 836801 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 6.8226. Min Range: -6.8226

Max Act: 5.6767. Min Act: -0.0000

Data Index: 204824 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 6.8226. Min Range: -6.8226

Max Act: 5.9435. Min Act: -0.0000

Data Index: 1184290 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 6.8226. Min Range: -6.8226

Max Act: 5.5203. Min Act: -0.0000

Data Index: 1088668 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 6.8226. Min Range: -6.8226

Max Act: 5.7975. Min Act: -0.0000

Data Index: 727357 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 6.8226. Min Range: -6.8226

Max Act: 5.7932. Min Act: -0.0000

Data Index: 346545 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 6.8226. Min Range: -6.8226

Max Act: 5.7390. Min Act: -0.0000

Data Index: 368380 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 6.8226. Min Range: -6.8226

Max Act: 5.6684. Min Act: -0.0000

Data Index: 529098 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 6.8226. Min Range: -6.8226

Max Act: 5.4134. Min Act: -0.0000

Data Index: 535637 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 6.8226. Min Range: -6.8226

Max Act: 5.6000. Min Act: -0.0000

Data Index: 389534 (C4 (Web Text))

Max Activating Token Index: 681