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

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

Neuron 2433 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.2450. Min Act: -0.0001

Data Index: 1633140 (Python Code)

Max Activating Token Index: 125

Text #1

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.7178. Min Act: -0.0001

Data Index: 1647338 (Python Code)

Max Activating Token Index: 87

Text #2

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.6776. Min Act: -0.0001

Data Index: 1637190 (Python Code)

Max Activating Token Index: 965

Text #3

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.5613. Min Act: -0.0001

Data Index: 1605167 (Python Code)

Max Activating Token Index: 21

Text #4

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.5573. Min Act: -0.0001

Data Index: 1446365 (Python Code)

Max Activating Token Index: 103

Text #5

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.3939. Min Act: -0.0001

Data Index: 1405942 (Python Code)

Max Activating Token Index: 549

Text #6

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.5019. Min Act: -0.0001

Data Index: 1492978 (Python Code)

Max Activating Token Index: 88

Text #7

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.5375. Min Act: -0.0001

Data Index: 1466622 (Python Code)

Max Activating Token Index: 349

Text #8

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.4199. Min Act: -0.0000

Data Index: 1467614 (Python Code)

Max Activating Token Index: 843

Text #9

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.1680. Min Act: -0.0000

Data Index: 1643924 (Python Code)

Max Activating Token Index: 279

Text #10

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.4240. Min Act: -0.0000

Data Index: 1625678 (Python Code)

Max Activating Token Index: 293

Text #11

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.2744. Min Act: -0.0000

Data Index: 1566396 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.2472. Min Act: -0.0001

Data Index: 1278860 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.1382. Min Act: -0.0001

Data Index: 1580059 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.2829. Min Act: -0.0000

Data Index: 1635342 (Python Code)

Max Activating Token Index: 224

Text #15

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.1924. Min Act: -0.0001

Data Index: 1530596 (Python Code)

Max Activating Token Index: 862

Text #16

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.0793. Min Act: -0.0000

Data Index: 1447368 (Python Code)

Max Activating Token Index: 971

Text #17

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.2681. Min Act: -0.0001

Data Index: 1560796 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.1374. Min Act: -0.0000

Data Index: 1125283 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.1310. Min Act: -0.0001

Data Index: 1391445 (Python Code)

Max Activating Token Index: 91