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

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

Neuron 3662 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.5815. Min Act: -0.0000

Data Index: 1218192 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.5596. Min Act: -0.0000

Data Index: 664339 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.3243. Min Act: -0.0000

Data Index: 785133 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.1977. Min Act: -0.0000

Data Index: 734867 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.2887. Min Act: -0.0000

Data Index: 432902 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.1986. Min Act: -0.0000

Data Index: 130270 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.1012. Min Act: -0.0000

Data Index: 442184 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.0578. Min Act: -0.0000

Data Index: 438373 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 1.5815. Min Range: -1.5815

Max Act: 0.9677. Min Act: -0.0000

Data Index: 725599 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.0179. Min Act: -0.0000

Data Index: 91455 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 1.5815. Min Range: -1.5815

Max Act: 0.9330. Min Act: -0.0000

Data Index: 805414 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 1.5815. Min Range: -1.5815

Max Act: 0.8628. Min Act: -0.0000

Data Index: 933355 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 1.5815. Min Range: -1.5815

Max Act: 0.8221. Min Act: -0.0000

Data Index: 745413 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 1.5815. Min Range: -1.5815

Max Act: 0.7898. Min Act: -0.0000

Data Index: 1242673 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 1.5815. Min Range: -1.5815

Max Act: 0.7553. Min Act: -0.0000

Data Index: 397749 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 1.5815. Min Range: -1.5815

Max Act: 0.7798. Min Act: -0.0000

Data Index: 1289971 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 1.5815. Min Range: -1.5815

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1087268 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 1.5815. Min Range: -1.5815

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1201834 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 1.5815. Min Range: -1.5815

Max Act: 0.7467. Min Act: -0.0000

Data Index: 810362 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 1.5815. Min Range: -1.5815

Max Act: 0.6757. Min Act: -0.0000

Data Index: 144096 (C4 (Web Text))

Max Activating Token Index: 168