Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1385 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.6709. Min Act: -0.0001

Data Index: 185929 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5952. Min Act: -0.0001

Data Index: 1343750 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5398. Min Act: -0.0002

Data Index: 56837 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5310. Min Act: -0.0002

Data Index: 365974 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4934. Min Act: -0.0001

Data Index: 281823 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5036. Min Act: -0.0002

Data Index: 831454 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5317. Min Act: -0.0001

Data Index: 656441 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4729. Min Act: -0.0001

Data Index: 1364528 (Python Code)

Max Activating Token Index: 157

Text #8

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5172. Min Act: -0.0001

Data Index: 91356 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4808. Min Act: -0.0001

Data Index: 786396 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4497. Min Act: -0.0002

Data Index: 951681 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4608. Min Act: -0.0001

Data Index: 661770 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4614. Min Act: -0.0001

Data Index: 1199291 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4680. Min Act: -0.0001

Data Index: 282841 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4461. Min Act: -0.0001

Data Index: 245277 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4241. Min Act: -0.0001

Data Index: 1501634 (Python Code)

Max Activating Token Index: 735

Text #16

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4501. Min Act: -0.0001

Data Index: 989098 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4376. Min Act: -0.0002

Data Index: 238262 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.4690. Min Act: -0.0002

Data Index: 1276850 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5055. Min Act: -0.0001

Data Index: 46844 (C4 (Web Text))

Max Activating Token Index: 875