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

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

Neuron 2646 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1167. Min Range: -1.1167

Max Act: 1.1167. Min Act: -0.0000

Data Index: 1587589 (Python Code)

Max Activating Token Index: 395

Text #1

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1406782 (Python Code)

Max Activating Token Index: 651

Text #2

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1383481 (Python Code)

Max Activating Token Index: 840

Text #3

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.7967. Min Act: -0.0000

Data Index: 130407 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8082. Min Act: -0.0000

Data Index: 1154926 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8118. Min Act: -0.0000

Data Index: 36971 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.7398. Min Act: -0.0000

Data Index: 43870 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1218232 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.6492. Min Act: -0.0000

Data Index: 846953 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.6322. Min Act: -0.0000

Data Index: 636978 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.6142. Min Act: -0.0000

Data Index: 1048974 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.5765. Min Act: -0.0000

Data Index: 674504 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1185100 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.6032. Min Act: -0.0000

Data Index: 468850 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.5805. Min Act: -0.0000

Data Index: 872780 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1327832 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.5438. Min Act: -0.0000

Data Index: 597359 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1074008 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1460338 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1518134 (Python Code)

Max Activating Token Index: 239