Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2129 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.5222. Min Act: -0.0001

Data Index: 1555809 (Python Code)

Max Activating Token Index: 897

Text #1

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4635. Min Act: -0.0001

Data Index: 1448591 (Python Code)

Max Activating Token Index: 92

Text #2

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4582. Min Act: -0.0001

Data Index: 1406211 (Python Code)

Max Activating Token Index: 84

Text #3

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3932. Min Act: -0.0001

Data Index: 1424106 (Python Code)

Max Activating Token Index: 548

Text #4

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3974. Min Act: -0.0001

Data Index: 1261819 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4334. Min Act: -0.0001

Data Index: 1378313 (Python Code)

Max Activating Token Index: 483

Text #6

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4282. Min Act: -0.0001

Data Index: 1632259 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3924. Min Act: -0.0001

Data Index: 359962 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3896. Min Act: -0.0001

Data Index: 1225319 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4244. Min Act: -0.0001

Data Index: 1635089 (Python Code)

Max Activating Token Index: 223

Text #10

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4078. Min Act: -0.0001

Data Index: 1370606 (Python Code)

Max Activating Token Index: 216

Text #11

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3806. Min Act: -0.0001

Data Index: 355392 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4163. Min Act: -0.0001

Data Index: 1533961 (Python Code)

Max Activating Token Index: 520

Text #13

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4020. Min Act: -0.0001

Data Index: 1550141 (Python Code)

Max Activating Token Index: 1020

Text #14

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4287. Min Act: -0.0001

Data Index: 1503431 (Python Code)

Max Activating Token Index: 637

Text #15

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4244. Min Act: -0.0001

Data Index: 1251293 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3824. Min Act: -0.0001

Data Index: 1537962 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3774. Min Act: -0.0001

Data Index: 1542594 (Python Code)

Max Activating Token Index: 161

Text #18

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4225. Min Act: -0.0001

Data Index: 838299 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3889. Min Act: -0.0001

Data Index: 1576340 (Python Code)

Max Activating Token Index: 660