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

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

Neuron 3065 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: 3.3260. Min Range: -3.3260

Max Act: 3.3260. Min Act: -0.0000

Data Index: 277953 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 3.3260. Min Range: -3.3260

Max Act: 2.4901. Min Act: -0.0000

Data Index: 1177545 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 3.3260. Min Range: -3.3260

Max Act: 2.5685. Min Act: -0.0000

Data Index: 85412 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 3.3260. Min Range: -3.3260

Max Act: 2.0277. Min Act: -0.0000

Data Index: 1084694 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.9516. Min Act: -0.0000

Data Index: 78272 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.8154. Min Act: -0.0000

Data Index: 975452 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.6906. Min Act: -0.0000

Data Index: 920949 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.5986. Min Act: -0.0000

Data Index: 836568 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.5936. Min Act: -0.0000

Data Index: 551917 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.5845. Min Act: -0.0000

Data Index: 342680 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.4920. Min Act: -0.0000

Data Index: 568212 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.6240. Min Act: -0.0000

Data Index: 266352 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.5301. Min Act: -0.0000

Data Index: 498289 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.5195. Min Act: -0.0000

Data Index: 811931 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.4925. Min Act: -0.0000

Data Index: 1116918 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.4439. Min Act: -0.0000

Data Index: 806093 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.5766. Min Act: -0.0000

Data Index: 1317037 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.4519. Min Act: -0.0000

Data Index: 348824 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.3984. Min Act: -0.0000

Data Index: 1266650 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 3.3260. Min Range: -3.3260

Max Act: 1.3919. Min Act: -0.0000

Data Index: 185230 (C4 (Web Text))

Max Activating Token Index: 698