Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2229 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7661. Min Act: -0.0001

Data Index: 126673 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.8076. Min Act: -0.0001

Data Index: 497385 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7840. Min Act: -0.0001

Data Index: 1305347 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.8131. Min Act: -0.0001

Data Index: 273264 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7679. Min Act: -0.0001

Data Index: 1001001 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6856. Min Act: -0.0001

Data Index: 109440 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7442. Min Act: -0.0001

Data Index: 127735 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.7064. Min Act: -0.0001

Data Index: 493938 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6929. Min Act: -0.0001

Data Index: 201156 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6111. Min Act: -0.0001

Data Index: 335626 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6564. Min Act: -0.0001

Data Index: 670768 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6335. Min Act: -0.0001

Data Index: 680007 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6041. Min Act: -0.0001

Data Index: 111669 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6345. Min Act: -0.0001

Data Index: 122021 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6123. Min Act: -0.0001

Data Index: 804783 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.5716. Min Act: -0.0001

Data Index: 1359244 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.5636. Min Act: -0.0001

Data Index: 1222724 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6021. Min Act: -0.0001

Data Index: 614401 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.5883. Min Act: -0.0001

Data Index: 439603 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.8131. Min Range: -0.8131

Max Act: 0.6145. Min Act: -0.0001

Data Index: 905307 (C4 (Web Text))

Max Activating Token Index: 777