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

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

Neuron 3512 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1243797 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1250159 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6929. Min Act: -0.0000

Data Index: 105699 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.5878. Min Act: -0.0000

Data Index: 999623 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1273431 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6584. Min Act: -0.0000

Data Index: 853686 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1327424 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.6243. Min Act: -0.0000

Data Index: 544324 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1114039 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.5350. Min Act: -0.0000

Data Index: 239583 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1031618 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1200382 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.5723. Min Act: -0.0000

Data Index: 265461 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1061366 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.5146. Min Act: -0.0000

Data Index: 298026 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.5339. Min Act: -0.0000

Data Index: 158127 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.4968. Min Act: -0.0000

Data Index: 875837 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.5186. Min Act: -0.0000

Data Index: 395938 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1026099 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.8473. Min Range: -0.8473

Max Act: 0.4836. Min Act: -0.0000

Data Index: 354265 (C4 (Web Text))

Max Activating Token Index: 878