Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3627 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.4525. Min Act: -0.0001

Data Index: 797253 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3888. Min Act: -0.0001

Data Index: 348375 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1169774 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3864. Min Act: -0.0001

Data Index: 1191464 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1015602 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1166443 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3430. Min Act: -0.0001

Data Index: 1282687 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3102. Min Act: -0.0001

Data Index: 1626404 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1221693 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3171. Min Act: -0.0000

Data Index: 525853 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1217500 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1241129 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3166. Min Act: -0.0001

Data Index: 193502 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3041. Min Act: -0.0000

Data Index: 266255 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3130. Min Act: -0.0000

Data Index: 606839 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3139. Min Act: -0.0000

Data Index: 429286 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3217. Min Act: -0.0001

Data Index: 1651138 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2871. Min Act: -0.0001

Data Index: 1602722 (Python Code)

Max Activating Token Index: 320

Text #18

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3030. Min Act: -0.0001

Data Index: 1571657 (Python Code)

Max Activating Token Index: 464

Text #19

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3025. Min Act: -0.0001

Data Index: 1638626 (Python Code)

Max Activating Token Index: 9