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

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

Neuron 3968 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1505. Min Range: -1.1505

Max Act: 1.1505. Min Act: -0.0002

Data Index: 388564 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 1.1505. Min Range: -1.1505

Max Act: 1.0259. Min Act: -0.0002

Data Index: 672642 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.9263. Min Act: -0.0002

Data Index: 859341 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.9184. Min Act: -0.0002

Data Index: 718493 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.9066. Min Act: -0.0002

Data Index: 340646 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.9180. Min Act: -0.0002

Data Index: 244488 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.8983. Min Act: -0.0002

Data Index: 410651 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.8878. Min Act: -0.0002

Data Index: 787005 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.8916. Min Act: -0.0002

Data Index: 1303112 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.8875. Min Act: -0.0002

Data Index: 1284116 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.8814. Min Act: -0.0003

Data Index: 758256 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.8648. Min Act: -0.0002

Data Index: 271456 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.8675. Min Act: -0.0003

Data Index: 419212 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.8498. Min Act: -0.0002

Data Index: 569038 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.8723. Min Act: -0.0002

Data Index: 989048 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.8513. Min Act: -0.0003

Data Index: 911525 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.8472. Min Act: -0.0003

Data Index: 154188 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.8407. Min Act: -0.0002

Data Index: 803087 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.8392. Min Act: -0.0002

Data Index: 194103 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.1505. Min Range: -1.1505

Max Act: 0.8440. Min Act: -0.0002

Data Index: 723146 (C4 (Web Text))

Max Activating Token Index: 126