Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 85 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.8690. Min Act: -0.0000

Data Index: 231105 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.7208. Min Act: -0.0000

Data Index: 331250 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.7059. Min Act: -0.0000

Data Index: 733823 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6456. Min Act: -0.0000

Data Index: 840337 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1066190 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5777. Min Act: -0.0000

Data Index: 586343 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6281. Min Act: -0.0000

Data Index: 657381 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5828. Min Act: -0.0000

Data Index: 780049 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5964. Min Act: -0.0000

Data Index: 7774 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1048038 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5709. Min Act: -0.0000

Data Index: 853189 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1297958 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5701. Min Act: -0.0000

Data Index: 819768 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5649. Min Act: -0.0000

Data Index: 54162 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5669. Min Act: -0.0000

Data Index: 606342 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1213503 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5577. Min Act: -0.0000

Data Index: 852631 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1210040 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5468. Min Act: -0.0000

Data Index: 297148 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.5400. Min Act: -0.0000

Data Index: 118844 (C4 (Web Text))

Max Activating Token Index: 558