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

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

Neuron 3387 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.9588. Min Act: -0.0001

Data Index: 252755 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1241728 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.8544. Min Act: -0.0001

Data Index: 435081 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1075457 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.8223. Min Act: -0.0001

Data Index: 705770 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.8218. Min Act: -0.0000

Data Index: 728366 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.8192. Min Act: -0.0000

Data Index: 785523 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7907. Min Act: -0.0000

Data Index: 594818 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7985. Min Act: -0.0001

Data Index: 134365 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7683. Min Act: -0.0000

Data Index: 799819 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7454. Min Act: -0.0000

Data Index: 153886 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7276. Min Act: -0.0001

Data Index: 1195983 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7308. Min Act: -0.0000

Data Index: 49623 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1023660 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.6925. Min Act: -0.0001

Data Index: 502154 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1151916 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7002. Min Act: -0.0001

Data Index: 330942 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7212. Min Act: -0.0001

Data Index: 1082621 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.6711. Min Act: -0.0000

Data Index: 954418 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1326640 (C4 (Web Text))

Max Activating Token Index: 743