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

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

Neuron 4558 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: 0.5090. Min Range: -0.5090

Max Act: 0.5090. Min Act: -0.0002

Data Index: 1531584 (Python Code)

Max Activating Token Index: 888

Text #1

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4403. Min Act: -0.0002

Data Index: 1625359 (Python Code)

Max Activating Token Index: 809

Text #2

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4341. Min Act: -0.0002

Data Index: 1524646 (Python Code)

Max Activating Token Index: 1000

Text #3

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4270. Min Act: -0.0002

Data Index: 1167650 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4407. Min Act: -0.0002

Data Index: 840523 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4217. Min Act: -0.0002

Data Index: 1012909 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4351. Min Act: -0.0002

Data Index: 711547 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4306. Min Act: -0.0002

Data Index: 1344363 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4165. Min Act: -0.0002

Data Index: 916340 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4087. Min Act: -0.0002

Data Index: 215141 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4121. Min Act: -0.0002

Data Index: 594963 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4154. Min Act: -0.0002

Data Index: 229700 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4056. Min Act: -0.0002

Data Index: 621123 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4092. Min Act: -0.0002

Data Index: 1575488 (Python Code)

Max Activating Token Index: 739

Text #14

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3982. Min Act: -0.0002

Data Index: 568690 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4066. Min Act: -0.0002

Data Index: 701432 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3991. Min Act: -0.0002

Data Index: 1072565 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.4049. Min Act: -0.0002

Data Index: 1323301 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3988. Min Act: -0.0002

Data Index: 1001424 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.5090. Min Range: -0.5090

Max Act: 0.3962. Min Act: -0.0002

Data Index: 554792 (C4 (Web Text))

Max Activating Token Index: 670