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

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

Neuron 3394 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.9148. Min Act: -0.0000

Data Index: 64073 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.8200. Min Act: -0.0000

Data Index: 577903 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.8862. Min Act: -0.0000

Data Index: 258820 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.8241. Min Act: -0.0000

Data Index: 715239 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1235577 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6756. Min Act: -0.0000

Data Index: 981288 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1228603 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1218835 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6527. Min Act: -0.0000

Data Index: 196185 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.5987. Min Act: -0.0000

Data Index: 611563 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6651. Min Act: -0.0000

Data Index: 652650 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1262669 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6398. Min Act: -0.0000

Data Index: 663191 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6261. Min Act: -0.0000

Data Index: 406299 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1029457 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6395. Min Act: -0.0000

Data Index: 817249 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6232. Min Act: -0.0000

Data Index: 84098 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.6079. Min Act: -0.0000

Data Index: 995143 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1193123 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.9148. Min Range: -0.9148

Max Act: 0.5820. Min Act: -0.0000

Data Index: 909712 (C4 (Web Text))

Max Activating Token Index: 960