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

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

Neuron 3637 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: 0.3146. Min Range: -0.3146

Max Act: 0.3146. Min Act: -0.0001

Data Index: 299896 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2952. Min Act: -0.0001

Data Index: 1156176 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2725. Min Act: -0.0001

Data Index: 394240 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2639. Min Act: -0.0001

Data Index: 829472 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2528. Min Act: -0.0001

Data Index: 173323 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2448. Min Act: -0.0001

Data Index: 317160 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1281013 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2050. Min Act: -0.0001

Data Index: 353339 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2004. Min Act: -0.0001

Data Index: 364673 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2168. Min Act: -0.0001

Data Index: 965228 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2051. Min Act: -0.0001

Data Index: 1339061 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2151. Min Act: -0.0001

Data Index: 1064698 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.1995. Min Act: -0.0001

Data Index: 1335553 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.1905. Min Act: -0.0001

Data Index: 809073 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.1841. Min Act: -0.0001

Data Index: 878824 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.1772. Min Act: -0.0001

Data Index: 1247006 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.1610. Min Act: -0.0001

Data Index: 289894 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.1504. Min Act: -0.0000

Data Index: 508513 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.1522. Min Act: -0.0000

Data Index: 896608 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.1510. Min Act: -0.0000

Data Index: 43139 (C4 (Web Text))

Max Activating Token Index: 186