Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2967 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.9630. Min Act: -0.0001

Data Index: 1249748 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7935. Min Act: -0.0001

Data Index: 918746 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7596. Min Act: -0.0001

Data Index: 1314343 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7032. Min Act: -0.0001

Data Index: 300411 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7171. Min Act: -0.0001

Data Index: 682185 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7416. Min Act: -0.0001

Data Index: 133410 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6834. Min Act: -0.0001

Data Index: 64026 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7352. Min Act: -0.0001

Data Index: 222741 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6480. Min Act: -0.0001

Data Index: 978688 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6928. Min Act: -0.0001

Data Index: 316472 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6610. Min Act: -0.0001

Data Index: 413332 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6264. Min Act: -0.0001

Data Index: 248809 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6184. Min Act: -0.0001

Data Index: 1298103 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6508. Min Act: -0.0001

Data Index: 751796 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6304. Min Act: -0.0001

Data Index: 683659 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6087. Min Act: -0.0001

Data Index: 1045014 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6271. Min Act: -0.0001

Data Index: 565544 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6478. Min Act: -0.0001

Data Index: 1081056 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5992. Min Act: -0.0001

Data Index: 381115 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5564. Min Act: -0.0001

Data Index: 869445 (C4 (Web Text))

Max Activating Token Index: 793