Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 441 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.9669. Min Act: -0.0000

Data Index: 1336449 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8171. Min Act: -0.0000

Data Index: 460309 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8791. Min Act: -0.0000

Data Index: 199473 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8326. Min Act: -0.0000

Data Index: 596381 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8196. Min Act: -0.0000

Data Index: 283690 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8007. Min Act: -0.0000

Data Index: 629300 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8148. Min Act: -0.0000

Data Index: 367128 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.7843. Min Act: -0.0000

Data Index: 999730 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1298242 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8241. Min Act: -0.0000

Data Index: 78480 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.7485. Min Act: -0.0000

Data Index: 664998 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8042. Min Act: -0.0000

Data Index: 141871 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.7690. Min Act: -0.0000

Data Index: 87003 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.7074. Min Act: -0.0000

Data Index: 65914 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.7557. Min Act: -0.0000

Data Index: 969424 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.7320. Min Act: -0.0000

Data Index: 786539 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6577. Min Act: -0.0000

Data Index: 840892 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6908. Min Act: -0.0000

Data Index: 686622 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6907. Min Act: -0.0000

Data Index: 716830 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.7127. Min Act: -0.0000

Data Index: 456516 (C4 (Web Text))

Max Activating Token Index: 441