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

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

Neuron 548 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.9179. Min Act: -0.0000

Data Index: 1309602 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.7542. Min Act: -0.0000

Data Index: 1212430 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.7277. Min Act: -0.0000

Data Index: 503313 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.7110. Min Act: -0.0000

Data Index: 485154 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.6180. Min Act: -0.0000

Data Index: 1236410 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 5.0289. Min Range: -5.0289

Max Act: 5.0289. Min Act: -0.0001

Data Index: 1271269 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.4855. Min Act: -0.0000

Data Index: 540661 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.3140. Min Act: -0.0000

Data Index: 1067424 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.0954. Min Act: -0.0000

Data Index: 660683 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.0938. Min Act: -0.0001

Data Index: 236899 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.0820. Min Act: -0.0000

Data Index: 357715 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.0674. Min Act: -0.0000

Data Index: 326852 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.0183. Min Act: -0.0001

Data Index: 718676 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.2999. Min Act: -0.0000

Data Index: 482271 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 5.0289. Min Range: -5.0289

Max Act: 3.6264. Min Act: -0.0000

Data Index: 1150162 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 5.0289. Min Range: -5.0289

Max Act: 3.7910. Min Act: -0.0000

Data Index: 591774 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 5.0289. Min Range: -5.0289

Max Act: 3.9026. Min Act: -0.0000

Data Index: 519506 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.4450. Min Act: -0.0000

Data Index: 1224211 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 5.0289. Min Range: -5.0289

Max Act: 3.7098. Min Act: -0.0001

Data Index: 720894 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 5.0289. Min Range: -5.0289

Max Act: 4.0539. Min Act: -0.0000

Data Index: 175131 (C4 (Web Text))

Max Activating Token Index: 957