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

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

Neuron 1159 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: 1.5770. Min Range: -1.5770

Max Act: 1.5770. Min Act: -0.0001

Data Index: 614153 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5122. Min Act: -0.0001

Data Index: 855714 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.4159. Min Act: -0.0001

Data Index: 111192 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.4796. Min Act: -0.0001

Data Index: 1033128 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.4352. Min Act: -0.0001

Data Index: 88120 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.4781. Min Act: -0.0000

Data Index: 838588 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.4137. Min Act: -0.0001

Data Index: 23691 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.4485. Min Act: -0.0001

Data Index: 297074 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.4267. Min Act: -0.0001

Data Index: 47665 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.3603. Min Act: -0.0001

Data Index: 553993 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.2786. Min Act: -0.0001

Data Index: 760458 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.3787. Min Act: -0.0001

Data Index: 837768 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.3741. Min Act: -0.0001

Data Index: 760459 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.3126. Min Act: -0.0000

Data Index: 282504 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.3096. Min Act: -0.0001

Data Index: 327673 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.3425. Min Act: -0.0001

Data Index: 1115178 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.2632. Min Act: -0.0001

Data Index: 168201 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.2614. Min Act: -0.0001

Data Index: 123815 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.2198. Min Act: -0.0001

Data Index: 156223 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.2143. Min Act: -0.0001

Data Index: 905532 (C4 (Web Text))

Max Activating Token Index: 196