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

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

Neuron 3870 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.8059. Min Act: -0.0000

Data Index: 2310 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1202400 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.8298. Min Act: -0.0000

Data Index: 569189 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1147252 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7192. Min Act: -0.0000

Data Index: 894854 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6493. Min Act: -0.0000

Data Index: 151788 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6546. Min Act: -0.0000

Data Index: 591603 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6199. Min Act: -0.0000

Data Index: 443595 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1061913 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1052445 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6726. Min Act: -0.0000

Data Index: 769285 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6119. Min Act: -0.0000

Data Index: 822034 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1032358 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6155. Min Act: -0.0000

Data Index: 191485 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6133. Min Act: -0.0000

Data Index: 479266 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1151618 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6062. Min Act: -0.0000

Data Index: 817128 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6415. Min Act: -0.0000

Data Index: 142788 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1246393 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1126217 (C4 (Web Text))

Max Activating Token Index: 895