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

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

Neuron 4900 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1224. Min Act: 0.0000

Data Index: 397740 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1359. Min Act: 0.0000

Data Index: 841015 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1242. Min Act: -0.0000

Data Index: 687008 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1081951 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1581647 (Python Code)

Max Activating Token Index: 830

Text #5

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1631134 (Python Code)

Max Activating Token Index: 123

Text #6

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1097. Min Act: 0.0000

Data Index: 1198133 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1060. Min Act: 0.0001

Data Index: 1289818 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1051. Min Act: -0.0000

Data Index: 255093 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1233265 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0999. Min Act: -0.0000

Data Index: 968323 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1477045 (Python Code)

Max Activating Token Index: 666

Text #12

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0998. Min Act: -0.0000

Data Index: 925306 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1540560 (Python Code)

Max Activating Token Index: 896

Text #14

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0978. Min Act: 0.0001

Data Index: 61275 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1572996 (Python Code)

Max Activating Token Index: 971

Text #16

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.1002. Min Act: 0.0000

Data Index: 764840 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0963. Min Act: 0.0000

Data Index: 742544 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0971. Min Act: -0.0000

Data Index: 464725 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.1359. Min Range: -0.1359

Max Act: 0.0985. Min Act: -0.0000

Data Index: 804772 (C4 (Web Text))

Max Activating Token Index: 88