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

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

Neuron 1785 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9682. Min Range: -3.9682

Max Act: 3.9682. Min Act: -0.0000

Data Index: 140415 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 3.9682. Min Range: -3.9682

Max Act: 2.0605. Min Act: -0.0000

Data Index: 447057 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.2248. Min Act: -0.0000

Data Index: 501892 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.1207. Min Act: -0.0000

Data Index: 1265551 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.1284. Min Act: -0.0000

Data Index: 1648033 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.0964. Min Act: -0.0000

Data Index: 1093617 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.0536. Min Act: -0.0000

Data Index: 1472512 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.0765. Min Act: -0.0000

Data Index: 54517 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.0695. Min Act: -0.0000

Data Index: 568903 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1481523 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1415864 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 3.9682. Min Range: -3.9682

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1425265 (Python Code)

Max Activating Token Index: 31

Text #12

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.0531. Min Act: -0.0000

Data Index: 1653013 (Python Code)

Max Activating Token Index: 37

Text #13

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.0357. Min Act: -0.0000

Data Index: 123137 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.0307. Min Act: -0.0000

Data Index: 204620 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1559581 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 3.9682. Min Range: -3.9682

Max Act: 0.9682. Min Act: -0.0000

Data Index: 386605 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.0212. Min Act: -0.0000

Data Index: 1631163 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.0041. Min Act: -0.0000

Data Index: 527138 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 3.9682. Min Range: -3.9682

Max Act: 1.0329. Min Act: -0.0000

Data Index: 1595249 (Python Code)

Max Activating Token Index: 11