Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5764 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.1035. Min Range: -5.1035

Max Act: 5.1035. Min Act: -0.0001

Data Index: 664682 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 5.1035. Min Range: -5.1035

Max Act: 3.5538. Min Act: -0.0001

Data Index: 645671 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 5.1035. Min Range: -5.1035

Max Act: 3.6892. Min Act: -0.0001

Data Index: 129668 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 5.1035. Min Range: -5.1035

Max Act: 2.8267. Min Act: -0.0001

Data Index: 420328 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 5.1035. Min Range: -5.1035

Max Act: 3.1146. Min Act: -0.0001

Data Index: 495882 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 5.1035. Min Range: -5.1035

Max Act: 3.0554. Min Act: -0.0001

Data Index: 1067836 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 5.1035. Min Range: -5.1035

Max Act: 3.4233. Min Act: -0.0001

Data Index: 331101 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 5.1035. Min Range: -5.1035

Max Act: 2.6429. Min Act: -0.0001

Data Index: 1090758 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 5.1035. Min Range: -5.1035

Max Act: 3.2192. Min Act: -0.0001

Data Index: 875432 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 5.1035. Min Range: -5.1035

Max Act: 2.8467. Min Act: -0.0001

Data Index: 109171 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 5.1035. Min Range: -5.1035

Max Act: 2.8509. Min Act: -0.0001

Data Index: 1025758 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 5.1035. Min Range: -5.1035

Max Act: 2.6929. Min Act: -0.0001

Data Index: 526572 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 5.1035. Min Range: -5.1035

Max Act: 2.9932. Min Act: -0.0001

Data Index: 789935 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 5.1035. Min Range: -5.1035

Max Act: 2.8232. Min Act: -0.0001

Data Index: 745840 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 5.1035. Min Range: -5.1035

Max Act: 2.5618. Min Act: -0.0001

Data Index: 1301660 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 5.1035. Min Range: -5.1035

Max Act: 2.6019. Min Act: -0.0001

Data Index: 134405 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 5.1035. Min Range: -5.1035

Max Act: 2.8669. Min Act: -0.0001

Data Index: 1349289 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 5.1035. Min Range: -5.1035

Max Act: 2.6088. Min Act: -0.0001

Data Index: 298804 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 5.1035. Min Range: -5.1035

Max Act: 2.9978. Min Act: -0.0001

Data Index: 884369 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 5.1035. Min Range: -5.1035

Max Act: 2.8715. Min Act: -0.0001

Data Index: 825039 (C4 (Web Text))

Max Activating Token Index: 231