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

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

Neuron 4913 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.8356. Min Act: -0.0001

Data Index: 909011 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7748. Min Act: -0.0001

Data Index: 148221 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7718. Min Act: -0.0001

Data Index: 208047 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7895. Min Act: -0.0001

Data Index: 1084015 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7624. Min Act: -0.0001

Data Index: 883026 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7110. Min Act: -0.0001

Data Index: 293564 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7383. Min Act: -0.0001

Data Index: 869590 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7254. Min Act: -0.0001

Data Index: 455402 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7185. Min Act: -0.0001

Data Index: 1123866 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7552. Min Act: -0.0001

Data Index: 640287 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.8275. Min Act: -0.0001

Data Index: 729104 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7086. Min Act: -0.0001

Data Index: 150158 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7357. Min Act: -0.0001

Data Index: 651783 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7375. Min Act: -0.0001

Data Index: 908512 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7279. Min Act: -0.0001

Data Index: 43785 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.5792. Min Act: -0.0001

Data Index: 1200250 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7660. Min Act: -0.0001

Data Index: 769246 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6875. Min Act: -0.0001

Data Index: 318139 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7555. Min Act: -0.0001

Data Index: 334324 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7474. Min Act: -0.0001

Data Index: 782572 (C4 (Web Text))

Max Activating Token Index: 327