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

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

Neuron 3974 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.9286. Min Act: -0.0002

Data Index: 1298248 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.9319. Min Act: -0.0002

Data Index: 72586 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.9100. Min Act: -0.0002

Data Index: 6425 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.8591. Min Act: -0.0002

Data Index: 140456 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.8433. Min Act: -0.0002

Data Index: 1341805 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.8428. Min Act: -0.0002

Data Index: 373708 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7865. Min Act: -0.0002

Data Index: 27689 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7833. Min Act: -0.0002

Data Index: 1229022 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7846. Min Act: -0.0002

Data Index: 1086351 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7705. Min Act: -0.0002

Data Index: 415219 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7764. Min Act: -0.0002

Data Index: 872154 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7292. Min Act: -0.0002

Data Index: 1161411 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7206. Min Act: -0.0002

Data Index: 1009606 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7394. Min Act: -0.0002

Data Index: 433174 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7027. Min Act: -0.0002

Data Index: 138350 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7110. Min Act: -0.0002

Data Index: 1588376 (Python Code)

Max Activating Token Index: 740

Text #16

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7197. Min Act: -0.0002

Data Index: 767586 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7020. Min Act: -0.0002

Data Index: 129670 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6908. Min Act: -0.0002

Data Index: 378413 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6872. Min Act: -0.0002

Data Index: 108204 (C4 (Web Text))

Max Activating Token Index: 108