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

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

Neuron 5770 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: 4.7214. Min Range: -4.7214

Max Act: 4.7214. Min Act: -0.0000

Data Index: 1415143 (Python Code)

Max Activating Token Index: 255

Text #1

Max Range: 4.7214. Min Range: -4.7214

Max Act: 4.3947. Min Act: -0.0000

Data Index: 1435770 (Python Code)

Max Activating Token Index: 114

Text #2

Max Range: 4.7214. Min Range: -4.7214

Max Act: 4.1224. Min Act: -0.0000

Data Index: 332483 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 4.7214. Min Range: -4.7214

Max Act: 4.4248. Min Act: -0.0000

Data Index: 1564802 (Python Code)

Max Activating Token Index: 993

Text #4

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.8334. Min Act: -0.0000

Data Index: 1486900 (Python Code)

Max Activating Token Index: 773

Text #5

Max Range: 4.7214. Min Range: -4.7214

Max Act: 4.2113. Min Act: -0.0000

Data Index: 1571271 (Python Code)

Max Activating Token Index: 874

Text #6

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.6369. Min Act: -0.0000

Data Index: 1161820 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.7143. Min Act: -0.0000

Data Index: 1457262 (Python Code)

Max Activating Token Index: 26

Text #8

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.6734. Min Act: -0.0000

Data Index: 1559120 (Python Code)

Max Activating Token Index: 161

Text #9

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.6827. Min Act: -0.0000

Data Index: 1414504 (Python Code)

Max Activating Token Index: 161

Text #10

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.5026. Min Act: -0.0000

Data Index: 1417893 (Python Code)

Max Activating Token Index: 777

Text #11

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.6591. Min Act: -0.0000

Data Index: 1516091 (Python Code)

Max Activating Token Index: 734

Text #12

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.6252. Min Act: -0.0000

Data Index: 1586790 (Python Code)

Max Activating Token Index: 766

Text #13

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.4556. Min Act: -0.0000

Data Index: 925980 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.7709. Min Act: -0.0000

Data Index: 1450096 (Python Code)

Max Activating Token Index: 1012

Text #15

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.4512. Min Act: -0.0000

Data Index: 1044049 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.2472. Min Act: -0.0000

Data Index: 859983 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.5439. Min Act: -0.0000

Data Index: 1033729 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.5632. Min Act: -0.0000

Data Index: 1255383 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 4.7214. Min Range: -4.7214

Max Act: 3.3894. Min Act: -0.0000

Data Index: 72054 (C4 (Web Text))

Max Activating Token Index: 839