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

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

Neuron 1068 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.5816. Min Act: -0.0001

Data Index: 1576688 (Python Code)

Max Activating Token Index: 411

Text #1

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.5650. Min Act: -0.0001

Data Index: 1643179 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1466987 (Python Code)

Max Activating Token Index: 41

Text #3

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.5710. Min Act: -0.0001

Data Index: 1384349 (Python Code)

Max Activating Token Index: 232

Text #4

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4873. Min Act: -0.0001

Data Index: 1542525 (Python Code)

Max Activating Token Index: 84

Text #5

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4613. Min Act: -0.0001

Data Index: 1441585 (Python Code)

Max Activating Token Index: 158

Text #6

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4481. Min Act: -0.0001

Data Index: 1098218 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4578. Min Act: -0.0001

Data Index: 1475831 (Python Code)

Max Activating Token Index: 618

Text #8

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4174. Min Act: -0.0001

Data Index: 1486491 (Python Code)

Max Activating Token Index: 201

Text #9

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4214. Min Act: -0.0001

Data Index: 1509034 (Python Code)

Max Activating Token Index: 149

Text #10

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4260. Min Act: -0.0001

Data Index: 1412996 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4273. Min Act: -0.0001

Data Index: 85515 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4249. Min Act: -0.0001

Data Index: 1240432 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4081. Min Act: -0.0001

Data Index: 103998 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4269. Min Act: -0.0001

Data Index: 954027 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4168. Min Act: -0.0001

Data Index: 1506656 (Python Code)

Max Activating Token Index: 77

Text #16

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3951. Min Act: -0.0001

Data Index: 1421812 (Python Code)

Max Activating Token Index: 885

Text #17

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4039. Min Act: -0.0000

Data Index: 841303 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3653. Min Act: -0.0001

Data Index: 1235936 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3998. Min Act: -0.0001

Data Index: 1368733 (Python Code)

Max Activating Token Index: 988