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

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

Neuron 1647 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: 1.1136. Min Range: -1.1136

Max Act: 1.1136. Min Act: -0.0001

Data Index: 768150 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 1.1136. Min Range: -1.1136

Max Act: 1.0520. Min Act: -0.0000

Data Index: 806961 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.1136. Min Range: -1.1136

Max Act: 1.0739. Min Act: -0.0000

Data Index: 387528 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 1.1136. Min Range: -1.1136

Max Act: 1.0549. Min Act: -0.0000

Data Index: 914887 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 1.1136. Min Range: -1.1136

Max Act: 1.0057. Min Act: -0.0000

Data Index: 224649 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.9831. Min Act: -0.0000

Data Index: 187306 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.9960. Min Act: -0.0001

Data Index: 267444 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.9559. Min Act: -0.0001

Data Index: 663189 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.9291. Min Act: -0.0000

Data Index: 855406 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8665. Min Act: -0.0000

Data Index: 493258 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8392. Min Act: -0.0001

Data Index: 1210999 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8292. Min Act: -0.0001

Data Index: 218375 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8108. Min Act: -0.0001

Data Index: 753704 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8189. Min Act: -0.0001

Data Index: 9279 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8429. Min Act: -0.0001

Data Index: 197391 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8100. Min Act: -0.0001

Data Index: 548880 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1315599 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.7585. Min Act: -0.0000

Data Index: 521987 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8087. Min Act: -0.0000

Data Index: 267910 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8326. Min Act: -0.0001

Data Index: 900983 (C4 (Web Text))

Max Activating Token Index: 546