Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2615 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.8158. Min Act: -0.0001

Data Index: 507049 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.6381. Min Act: -0.0000

Data Index: 386254 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.8125. Min Act: -0.0000

Data Index: 508705 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.9181. Min Act: -0.0000

Data Index: 195255 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.5153. Min Act: -0.0000

Data Index: 86961 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.4888. Min Act: -0.0000

Data Index: 671328 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.4663. Min Act: -0.0000

Data Index: 139729 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.5419. Min Act: -0.0000

Data Index: 1177636 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.3940. Min Act: -0.0000

Data Index: 71093 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.3436. Min Act: -0.0000

Data Index: 359795 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.2080. Min Act: -0.0000

Data Index: 237046 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.2825. Min Act: -0.0000

Data Index: 889980 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.2553. Min Act: -0.0000

Data Index: 424407 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.9130. Min Act: -0.0000

Data Index: 721205 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 2.9181. Min Range: -2.9181

Max Act: 1.9885. Min Act: -0.0000

Data Index: 1262715 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.1924. Min Act: -0.0001

Data Index: 339742 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.3083. Min Act: -0.0001

Data Index: 1140376 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.0876. Min Act: -0.0000

Data Index: 1259457 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.0376. Min Act: -0.0000

Data Index: 1269459 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 2.9181. Min Range: -2.9181

Max Act: 2.1459. Min Act: -0.0000

Data Index: 655504 (C4 (Web Text))

Max Activating Token Index: 236