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

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

Neuron 4194 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.7641. Min Act: -0.0000

Data Index: 831310 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.1287. Min Act: -0.0000

Data Index: 974070 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.3177. Min Act: -0.0000

Data Index: 1245883 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.2574. Min Act: -0.0000

Data Index: 306054 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.2272. Min Act: -0.0000

Data Index: 1575083 (Python Code)

Max Activating Token Index: 51

Text #5

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.1404. Min Act: -0.0000

Data Index: 1402004 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.3577. Min Act: -0.0000

Data Index: 1643795 (Python Code)

Max Activating Token Index: 110

Text #7

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.2091. Min Act: -0.0000

Data Index: 243409 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.2006. Min Act: -0.0000

Data Index: 948942 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.1454. Min Act: -0.0000

Data Index: 1535605 (Python Code)

Max Activating Token Index: 342

Text #10

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.1907. Min Act: -0.0000

Data Index: 98360 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.1841. Min Act: -0.0000

Data Index: 1493286 (Python Code)

Max Activating Token Index: 2

Text #12

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.1356. Min Act: -0.0000

Data Index: 1498994 (Python Code)

Max Activating Token Index: 281

Text #13

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1623189 (Python Code)

Max Activating Token Index: 989

Text #14

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.1571. Min Act: -0.0000

Data Index: 321415 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.1248. Min Act: -0.0000

Data Index: 1656865 (Python Code)

Max Activating Token Index: 902

Text #16

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.1467. Min Act: -0.0000

Data Index: 1646659 (Python Code)

Max Activating Token Index: 347

Text #17

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.1063. Min Act: -0.0000

Data Index: 1471567 (Python Code)

Max Activating Token Index: 740

Text #18

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.1704. Min Act: -0.0000

Data Index: 915676 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.7641. Min Range: -1.7641

Max Act: 1.1144. Min Act: -0.0000

Data Index: 889235 (C4 (Web Text))

Max Activating Token Index: 366