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

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

Neuron 328 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.5913. Min Act: -0.0000

Data Index: 1446398 (Python Code)

Max Activating Token Index: 639

Text #1

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.5747. Min Act: -0.0000

Data Index: 557290 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.5522. Min Act: -0.0000

Data Index: 1550098 (Python Code)

Max Activating Token Index: 1012

Text #3

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.5886. Min Act: -0.0000

Data Index: 1607146 (Python Code)

Max Activating Token Index: 797

Text #4

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.2169. Min Act: -0.0000

Data Index: 1471870 (Python Code)

Max Activating Token Index: 719

Text #5

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.3730. Min Act: -0.0000

Data Index: 652166 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.0386. Min Act: -0.0000

Data Index: 1508696 (Python Code)

Max Activating Token Index: 821

Text #7

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.2368. Min Act: -0.0000

Data Index: 125856 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.4207. Min Act: -0.0000

Data Index: 1386831 (Python Code)

Max Activating Token Index: 721

Text #9

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.2232. Min Act: -0.0000

Data Index: 180295 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.1030. Min Act: -0.0000

Data Index: 1185032 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.2727. Min Act: -0.0000

Data Index: 1552590 (Python Code)

Max Activating Token Index: 291

Text #12

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.2294. Min Act: -0.0000

Data Index: 320556 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.0627. Min Act: -0.0000

Data Index: 573135 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.1638. Min Act: -0.0000

Data Index: 1612210 (Python Code)

Max Activating Token Index: 877

Text #15

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.0559. Min Act: -0.0000

Data Index: 1428223 (Python Code)

Max Activating Token Index: 185

Text #16

Max Range: 2.5913. Min Range: -2.5913

Max Act: 1.9363. Min Act: -0.0000

Data Index: 1602643 (Python Code)

Max Activating Token Index: 84

Text #17

Max Range: 2.5913. Min Range: -2.5913

Max Act: 1.9819. Min Act: -0.0000

Data Index: 1612742 (Python Code)

Max Activating Token Index: 345

Text #18

Max Range: 2.5913. Min Range: -2.5913

Max Act: 1.9642. Min Act: -0.0000

Data Index: 1537873 (Python Code)

Max Activating Token Index: 206

Text #19

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.0425. Min Act: -0.0000

Data Index: 1551844 (Python Code)

Max Activating Token Index: 601