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

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

Neuron 1841 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.4905. Min Act: -0.0001

Data Index: 1024646 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.4923. Min Act: -0.0001

Data Index: 1279831 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.4460. Min Act: -0.0001

Data Index: 596618 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.4469. Min Act: -0.0001

Data Index: 938198 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.4201. Min Act: -0.0001

Data Index: 1017950 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.4187. Min Act: -0.0001

Data Index: 923850 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.4198. Min Act: -0.0001

Data Index: 654323 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3846. Min Act: -0.0001

Data Index: 214509 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.4278. Min Act: -0.0001

Data Index: 72785 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.4016. Min Act: -0.0001

Data Index: 603279 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3884. Min Act: -0.0001

Data Index: 391551 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.4062. Min Act: -0.0001

Data Index: 1136959 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.4575. Min Act: -0.0001

Data Index: 731421 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3786. Min Act: -0.0001

Data Index: 520363 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.4534. Min Act: -0.0001

Data Index: 231452 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.4301. Min Act: -0.0001

Data Index: 1249113 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3953. Min Act: -0.0001

Data Index: 766462 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3659. Min Act: -0.0001

Data Index: 509719 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3800. Min Act: -0.0001

Data Index: 13867 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3411. Min Act: -0.0001

Data Index: 773770 (C4 (Web Text))

Max Activating Token Index: 747