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

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

Neuron 4030 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: 0.8325. Min Range: -0.8325

Max Act: 0.8325. Min Act: -0.0001

Data Index: 1228720 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.8304. Min Act: -0.0001

Data Index: 1053983 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.8262. Min Act: -0.0001

Data Index: 1233137 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.8021. Min Act: -0.0001

Data Index: 1291979 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7739. Min Act: -0.0001

Data Index: 96225 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1612936 (Python Code)

Max Activating Token Index: 499

Text #6

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1522608 (Python Code)

Max Activating Token Index: 520

Text #7

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7521. Min Act: -0.0001

Data Index: 76470 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7787. Min Act: -0.0001

Data Index: 987316 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7620. Min Act: -0.0001

Data Index: 791694 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7806. Min Act: -0.0001

Data Index: 1246586 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7537. Min Act: -0.0001

Data Index: 913595 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7399. Min Act: -0.0001

Data Index: 1638867 (Python Code)

Max Activating Token Index: 297

Text #13

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1368846 (Python Code)

Max Activating Token Index: 342

Text #14

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7869. Min Act: -0.0001

Data Index: 732603 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7062. Min Act: -0.0001

Data Index: 1315414 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7211. Min Act: -0.0001

Data Index: 633055 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1574266 (Python Code)

Max Activating Token Index: 89

Text #18

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7192. Min Act: -0.0001

Data Index: 1073542 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1396745 (Python Code)

Max Activating Token Index: 389