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

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

Neuron 3887 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: 0.5130. Min Range: -0.5130

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1046605 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1269375 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4586. Min Act: -0.0000

Data Index: 645959 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4876. Min Act: -0.0000

Data Index: 127482 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4853. Min Act: -0.0000

Data Index: 808726 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4617. Min Act: -0.0000

Data Index: 378380 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1407 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4846. Min Act: -0.0000

Data Index: 13711 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4615. Min Act: -0.0000

Data Index: 359375 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4614. Min Act: -0.0000

Data Index: 45734 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4559. Min Act: -0.0000

Data Index: 254542 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4550. Min Act: -0.0000

Data Index: 191778 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1310722 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1233569 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4259. Min Act: -0.0000

Data Index: 189835 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4501. Min Act: -0.0000

Data Index: 997371 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4187. Min Act: -0.0000

Data Index: 826341 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1276421 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1006970 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.5130. Min Range: -0.5130

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1010486 (C4 (Web Text))

Max Activating Token Index: 292