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

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

Neuron 2482 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: 0.3450. Min Range: -0.3450

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1378759 (Python Code)

Max Activating Token Index: 515

Text #1

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1472223 (Python Code)

Max Activating Token Index: 777

Text #2

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3148. Min Act: -0.0000

Data Index: 1561246 (Python Code)

Max Activating Token Index: 400

Text #3

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3057. Min Act: -0.0000

Data Index: 421030 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2872. Min Act: -0.0000

Data Index: 350912 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3146. Min Act: -0.0000

Data Index: 178870 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1605381 (Python Code)

Max Activating Token Index: 320

Text #7

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3302. Min Act: -0.0000

Data Index: 95572 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1426007 (Python Code)

Max Activating Token Index: 850

Text #9

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1049980 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1157657 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2921. Min Act: -0.0000

Data Index: 952812 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1470380 (Python Code)

Max Activating Token Index: 138

Text #13

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2782. Min Act: -0.0000

Data Index: 500915 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2928. Min Act: -0.0000

Data Index: 514740 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1470393 (Python Code)

Max Activating Token Index: 868

Text #16

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1031882 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1474476 (Python Code)

Max Activating Token Index: 699

Text #18

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1073431 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2796. Min Act: -0.0000

Data Index: 977632 (C4 (Web Text))

Max Activating Token Index: 499