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

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

Neuron 646 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1518. Min Act: -0.0001

Data Index: 819003 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1322. Min Act: -0.0001

Data Index: 3616 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1412. Min Act: -0.0001

Data Index: 916280 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1298. Min Act: -0.0001

Data Index: 816439 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1241. Min Act: -0.0001

Data Index: 936608 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1283. Min Act: -0.0001

Data Index: 155046 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1268. Min Act: -0.0001

Data Index: 172336 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1299. Min Act: -0.0001

Data Index: 790219 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1240. Min Act: -0.0001

Data Index: 982579 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1100365 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1163. Min Act: -0.0001

Data Index: 311919 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1127. Min Act: -0.0001

Data Index: 401086 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1244. Min Act: -0.0001

Data Index: 124786 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1106. Min Act: -0.0001

Data Index: 941199 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1026073 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1056. Min Act: -0.0001

Data Index: 684384 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1145. Min Act: -0.0001

Data Index: 571828 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1036. Min Act: -0.0001

Data Index: 260765 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1144. Min Act: -0.0001

Data Index: 970254 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.0979. Min Act: -0.0001

Data Index: 77015 (C4 (Web Text))

Max Activating Token Index: 171