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

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

Neuron 2735 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.4395. Min Act: -0.0000

Data Index: 1614040 (Python Code)

Max Activating Token Index: 236

Text #1

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.1202. Min Act: -0.0000

Data Index: 1373750 (Python Code)

Max Activating Token Index: 779

Text #2

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.1887. Min Act: -0.0000

Data Index: 211686 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.1547. Min Act: -0.0000

Data Index: 1538012 (Python Code)

Max Activating Token Index: 665

Text #4

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.0320. Min Act: -0.0000

Data Index: 1606786 (Python Code)

Max Activating Token Index: 551

Text #5

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.0360. Min Act: -0.0000

Data Index: 1627355 (Python Code)

Max Activating Token Index: 556

Text #6

Max Range: 1.4395. Min Range: -1.4395

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1463172 (Python Code)

Max Activating Token Index: 475

Text #7

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1396212 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1558150 (Python Code)

Max Activating Token Index: 327

Text #9

Max Range: 1.4395. Min Range: -1.4395

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1441564 (Python Code)

Max Activating Token Index: 584

Text #10

Max Range: 1.4395. Min Range: -1.4395

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1545133 (Python Code)

Max Activating Token Index: 517

Text #11

Max Range: 1.4395. Min Range: -1.4395

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1554513 (Python Code)

Max Activating Token Index: 505

Text #12

Max Range: 1.4395. Min Range: -1.4395

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1457299 (Python Code)

Max Activating Token Index: 905

Text #13

Max Range: 1.4395. Min Range: -1.4395

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1554402 (Python Code)

Max Activating Token Index: 143

Text #14

Max Range: 1.4395. Min Range: -1.4395

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1549603 (Python Code)

Max Activating Token Index: 176

Text #15

Max Range: 1.4395. Min Range: -1.4395

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1487943 (Python Code)

Max Activating Token Index: 849

Text #16

Max Range: 1.4395. Min Range: -1.4395

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1628071 (Python Code)

Max Activating Token Index: 136

Text #17

Max Range: 1.4395. Min Range: -1.4395

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1611171 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 1.4395. Min Range: -1.4395

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1541143 (Python Code)

Max Activating Token Index: 810

Text #19

Max Range: 1.4395. Min Range: -1.4395

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1336605 (C4 (Web Text))

Max Activating Token Index: 984