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

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

Neuron 3615 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0993. Min Act: -0.0001

Data Index: 193825 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.1048. Min Act: -0.0000

Data Index: 395346 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.1018. Min Act: -0.0001

Data Index: 203748 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1041045 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0848. Min Act: -0.0000

Data Index: 701194 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0847. Min Act: -0.0000

Data Index: 73608 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0907. Min Act: -0.0001

Data Index: 315323 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0844. Min Act: -0.0000

Data Index: 912401 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0844. Min Act: -0.0001

Data Index: 190100 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0831. Min Act: -0.0001

Data Index: 617992 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0834. Min Act: -0.0001

Data Index: 1094119 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0858. Min Act: -0.0001

Data Index: 826090 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1106402 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0812. Min Act: -0.0001

Data Index: 735891 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0812. Min Act: -0.0000

Data Index: 367111 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0814. Min Act: -0.0001

Data Index: 957962 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0802. Min Act: -0.0000

Data Index: 652673 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0776. Min Act: -0.0000

Data Index: 463938 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0738. Min Act: -0.0000

Data Index: 822895 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0745. Min Act: -0.0000

Data Index: 1042681 (C4 (Web Text))

Max Activating Token Index: 200