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

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

Neuron 4675 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.5050. Min Act: -0.0000

Data Index: 1534779 (Python Code)

Max Activating Token Index: 251

Text #1

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.6257. Min Act: -0.0000

Data Index: 1610305 (Python Code)

Max Activating Token Index: 748

Text #2

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.4115. Min Act: -0.0000

Data Index: 1020678 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.2593. Min Act: -0.0000

Data Index: 1555372 (Python Code)

Max Activating Token Index: 408

Text #4

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.1157. Min Act: -0.0000

Data Index: 626314 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.3279. Min Act: -0.0000

Data Index: 1473703 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.1636. Min Act: -0.0000

Data Index: 1383265 (Python Code)

Max Activating Token Index: 758

Text #7

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.1080. Min Act: 0.0000

Data Index: 1484566 (Python Code)

Max Activating Token Index: 157

Text #8

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.2287. Min Act: -0.0000

Data Index: 1253830 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.1427. Min Act: -0.0000

Data Index: 1397654 (Python Code)

Max Activating Token Index: 35

Text #10

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.1165. Min Act: -0.0000

Data Index: 1407920 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.1091. Min Act: -0.0000

Data Index: 1612704 (Python Code)

Max Activating Token Index: 40

Text #12

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.0606. Min Act: -0.0000

Data Index: 24069 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.1957. Min Act: -0.0000

Data Index: 383230 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.1865. Min Act: -0.0000

Data Index: 484593 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.0652. Min Act: -0.0000

Data Index: 1590230 (Python Code)

Max Activating Token Index: 559

Text #16

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.0408. Min Act: -0.0000

Data Index: 1424878 (Python Code)

Max Activating Token Index: 372

Text #17

Max Range: 2.6257. Min Range: -2.6257

Max Act: 1.9873. Min Act: -0.0000

Data Index: 1417379 (Python Code)

Max Activating Token Index: 282

Text #18

Max Range: 2.6257. Min Range: -2.6257

Max Act: 1.9769. Min Act: -0.0000

Data Index: 195007 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 2.6257. Min Range: -2.6257

Max Act: 2.0660. Min Act: -0.0000

Data Index: 125496 (C4 (Web Text))

Max Activating Token Index: 222