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

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

Neuron 3343 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2359. Min Range: -1.2359

Max Act: 1.1440. Min Act: -0.0000

Data Index: 1623890 (Python Code)

Max Activating Token Index: 321

Text #1

Max Range: 1.2359. Min Range: -1.2359

Max Act: 1.2359. Min Act: -0.0000

Data Index: 1638986 (Python Code)

Max Activating Token Index: 917

Text #2

Max Range: 1.2359. Min Range: -1.2359

Max Act: 1.0665. Min Act: -0.0000

Data Index: 1371056 (Python Code)

Max Activating Token Index: 16

Text #3

Max Range: 1.2359. Min Range: -1.2359

Max Act: 1.0809. Min Act: -0.0001

Data Index: 1306872 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.9897. Min Act: -0.0000

Data Index: 1415972 (Python Code)

Max Activating Token Index: 411

Text #5

Max Range: 1.2359. Min Range: -1.2359

Max Act: 1.0144. Min Act: -0.0000

Data Index: 1592624 (Python Code)

Max Activating Token Index: 732

Text #6

Max Range: 1.2359. Min Range: -1.2359

Max Act: 1.0729. Min Act: -0.0000

Data Index: 1612341 (Python Code)

Max Activating Token Index: 236

Text #7

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.9766. Min Act: -0.0000

Data Index: 1648695 (Python Code)

Max Activating Token Index: 997

Text #8

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.9664. Min Act: -0.0000

Data Index: 1576211 (Python Code)

Max Activating Token Index: 72

Text #9

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.9425. Min Act: -0.0001

Data Index: 509123 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1546198 (Python Code)

Max Activating Token Index: 383

Text #11

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.9479. Min Act: -0.0000

Data Index: 1370736 (Python Code)

Max Activating Token Index: 271

Text #12

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.9495. Min Act: -0.0001

Data Index: 374057 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.9125. Min Act: -0.0000

Data Index: 1558339 (Python Code)

Max Activating Token Index: 969

Text #14

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.9100. Min Act: -0.0001

Data Index: 1503405 (Python Code)

Max Activating Token Index: 778

Text #15

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.9216. Min Act: -0.0000

Data Index: 266607 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.9298. Min Act: -0.0000

Data Index: 1433183 (Python Code)

Max Activating Token Index: 622

Text #17

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1442768 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1559496 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 1.2359. Min Range: -1.2359

Max Act: 0.9069. Min Act: -0.0001

Data Index: 1053385 (C4 (Web Text))

Max Activating Token Index: 742