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

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

Neuron 785 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0238. Min Range: -1.0238

Max Act: 1.0000. Min Act: -0.0001

Data Index: 1223874 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 1.0238. Min Range: -1.0238

Max Act: 1.0078. Min Act: -0.0000

Data Index: 239126 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 1.0238. Min Range: -1.0238

Max Act: 1.0238. Min Act: -0.0001

Data Index: 480857 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9865. Min Act: -0.0000

Data Index: 187018 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9730. Min Act: -0.0000

Data Index: 871887 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8821. Min Act: -0.0001

Data Index: 744966 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.9293. Min Act: -0.0000

Data Index: 626244 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8534. Min Act: -0.0001

Data Index: 618366 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8369. Min Act: -0.0001

Data Index: 178107 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8802. Min Act: -0.0001

Data Index: 482563 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8205. Min Act: -0.0000

Data Index: 830365 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7664. Min Act: -0.0000

Data Index: 162757 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8523. Min Act: -0.0000

Data Index: 520441 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8198. Min Act: -0.0000

Data Index: 826554 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7961. Min Act: -0.0001

Data Index: 507663 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8152. Min Act: -0.0001

Data Index: 426238 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8097. Min Act: -0.0001

Data Index: 786269 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8075. Min Act: -0.0001

Data Index: 698269 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7840. Min Act: -0.0000

Data Index: 487941 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8266. Min Act: -0.0000

Data Index: 433215 (C4 (Web Text))

Max Activating Token Index: 186