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

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

Neuron 5015 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.9678. Min Act: -0.0000

Data Index: 1271606 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.7415. Min Act: -0.0000

Data Index: 548403 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.9070. Min Act: -0.0000

Data Index: 480455 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.7401. Min Act: -0.0000

Data Index: 1167465 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.6694. Min Act: -0.0000

Data Index: 1010614 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.7249. Min Act: -0.0000

Data Index: 538180 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.7156. Min Act: -0.0000

Data Index: 674994 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.6015. Min Act: -0.0000

Data Index: 1212843 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.4231. Min Act: -0.0000

Data Index: 660639 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.7696. Min Act: -0.0000

Data Index: 536874 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.5751. Min Act: -0.0000

Data Index: 704077 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.5289. Min Act: -0.0000

Data Index: 392950 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.5172. Min Act: -0.0000

Data Index: 436486 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.3153. Min Act: -0.0000

Data Index: 1296807 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.5701. Min Act: -0.0000

Data Index: 46131 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.4347. Min Act: -0.0000

Data Index: 1356414 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.3185. Min Act: -0.0000

Data Index: 308777 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.4703. Min Act: -0.0000

Data Index: 983750 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.3833. Min Act: -0.0000

Data Index: 1160362 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 1.9678. Min Range: -1.9678

Max Act: 1.3564. Min Act: -0.0000

Data Index: 550304 (C4 (Web Text))

Max Activating Token Index: 845