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

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

Neuron 3512 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: 0.8330. Min Range: -0.8330

Max Act: 0.8330. Min Act: -0.0001

Data Index: 1291207 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7884. Min Act: -0.0001

Data Index: 874179 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.8145. Min Act: -0.0001

Data Index: 704912 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7921. Min Act: -0.0001

Data Index: 1156119 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7408. Min Act: -0.0001

Data Index: 1173512 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7379. Min Act: -0.0001

Data Index: 276862 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7467. Min Act: -0.0001

Data Index: 460714 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6949. Min Act: -0.0001

Data Index: 1062211 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6857. Min Act: -0.0001

Data Index: 1068110 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7459. Min Act: -0.0001

Data Index: 1086145 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7262. Min Act: -0.0001

Data Index: 153105 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7055. Min Act: -0.0001

Data Index: 195434 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6747. Min Act: -0.0001

Data Index: 1129438 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6987. Min Act: -0.0001

Data Index: 239495 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6923. Min Act: -0.0001

Data Index: 338084 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6727. Min Act: -0.0001

Data Index: 884903 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7385. Min Act: -0.0001

Data Index: 1185286 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6611. Min Act: -0.0001

Data Index: 128831 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6741. Min Act: -0.0001

Data Index: 373826 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6313. Min Act: -0.0001

Data Index: 1352800 (C4 (Web Text))

Max Activating Token Index: 13