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

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

Neuron 517 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: 1.4127. Min Range: -1.4127

Max Act: 1.4075. Min Act: -0.0001

Data Index: 474956 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.3707. Min Act: -0.0001

Data Index: 650518 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.4127. Min Act: -0.0001

Data Index: 134180 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.1797. Min Act: -0.0000

Data Index: 1631481 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.1225. Min Act: -0.0001

Data Index: 242176 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.0877. Min Act: -0.0001

Data Index: 127171 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.1863. Min Act: -0.0001

Data Index: 868038 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.1725. Min Act: -0.0001

Data Index: 107043 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.1317. Min Act: -0.0001

Data Index: 1247810 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.0941. Min Act: -0.0001

Data Index: 387826 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.1555. Min Act: -0.0001

Data Index: 313020 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.1228. Min Act: -0.0001

Data Index: 959060 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.1060. Min Act: -0.0001

Data Index: 1591431 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.0367. Min Act: -0.0001

Data Index: 1641548 (Python Code)

Max Activating Token Index: 808

Text #14

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.1257. Min Act: -0.0000

Data Index: 1485200 (Python Code)

Max Activating Token Index: 586

Text #15

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.0627. Min Act: -0.0001

Data Index: 216255 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.0296. Min Act: -0.0001

Data Index: 566904 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 1.4127. Min Range: -1.4127

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1420537 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 1.4127. Min Range: -1.4127

Max Act: 0.9922. Min Act: -0.0001

Data Index: 284419 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 1.4127. Min Range: -1.4127

Max Act: 1.0907. Min Act: -0.0001

Data Index: 259623 (C4 (Web Text))

Max Activating Token Index: 243