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

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

Neuron 2062 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0843. Min Range: -2.0843

Max Act: 2.0843. Min Act: -0.0000

Data Index: 1096758 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.8055. Min Act: -0.0000

Data Index: 596218 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.8557. Min Act: -0.0000

Data Index: 1637879 (Python Code)

Max Activating Token Index: 248

Text #3

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.5257. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.4011. Min Act: -0.0000

Data Index: 1584322 (Python Code)

Max Activating Token Index: 777

Text #5

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.4347. Min Act: -0.0000

Data Index: 1554087 (Python Code)

Max Activating Token Index: 433

Text #6

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.4027. Min Act: -0.0000

Data Index: 681202 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.3463. Min Act: -0.0000

Data Index: 942805 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.3705. Min Act: -0.0000

Data Index: 1178213 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.3618. Min Act: -0.0000

Data Index: 257269 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.3407. Min Act: -0.0000

Data Index: 324488 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.3504. Min Act: -0.0000

Data Index: 1573078 (Python Code)

Max Activating Token Index: 182

Text #12

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.4221. Min Act: -0.0000

Data Index: 1492170 (Python Code)

Max Activating Token Index: 799

Text #13

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.2951. Min Act: -0.0000

Data Index: 1227870 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.2206. Min Act: -0.0000

Data Index: 873393 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.2888. Min Act: -0.0000

Data Index: 587322 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.2058. Min Act: -0.0000

Data Index: 1194816 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.2346. Min Act: -0.0000

Data Index: 194357 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.2499. Min Act: -0.0000

Data Index: 933503 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 2.0843. Min Range: -2.0843

Max Act: 1.2020. Min Act: -0.0000

Data Index: 1613544 (Python Code)

Max Activating Token Index: 223