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

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

Neuron 3713 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.7659. Min Act: -0.0001

Data Index: 51459 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.3993. Min Act: -0.0001

Data Index: 174463 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.3365. Min Act: -0.0000

Data Index: 761277 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.3831. Min Act: -0.0000

Data Index: 1299222 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.1671. Min Act: -0.0000

Data Index: 459069 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.1669. Min Act: -0.0001

Data Index: 773115 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.1821. Min Act: -0.0001

Data Index: 757285 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.0709. Min Act: -0.0000

Data Index: 640891 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.1324. Min Act: -0.0000

Data Index: 604450 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.1093. Min Act: -0.0000

Data Index: 241975 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.0990. Min Act: -0.0001

Data Index: 907696 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.0680. Min Act: -0.0001

Data Index: 1139284 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 1.7659. Min Range: -1.7659

Max Act: 0.9971. Min Act: -0.0001

Data Index: 889693 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.0290. Min Act: -0.0001

Data Index: 787819 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.0479. Min Act: -0.0001

Data Index: 1203293 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.0770. Min Act: -0.0001

Data Index: 54522 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 1.7659. Min Range: -1.7659

Max Act: 1.0370. Min Act: -0.0000

Data Index: 247669 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 1.7659. Min Range: -1.7659

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1120632 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 1.7659. Min Range: -1.7659

Max Act: 0.9417. Min Act: -0.0001

Data Index: 469688 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 1.7659. Min Range: -1.7659

Max Act: 0.9160. Min Act: -0.0001

Data Index: 644364 (C4 (Web Text))

Max Activating Token Index: 733