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

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

Neuron 3149 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: 3.6354. Min Range: -3.6354

Max Act: 3.6354. Min Act: -0.0000

Data Index: 1044792 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 3.6354. Min Range: -3.6354

Max Act: 3.5501. Min Act: -0.0000

Data Index: 184145 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.7654. Min Act: -0.0000

Data Index: 1058959 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.7128. Min Act: -0.0000

Data Index: 261856 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.6604. Min Act: -0.0000

Data Index: 880752 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.5170. Min Act: -0.0000

Data Index: 355129 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.2987. Min Act: -0.0000

Data Index: 556770 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.4248. Min Act: -0.0000

Data Index: 261965 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.4001. Min Act: -0.0000

Data Index: 5566 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.2819. Min Act: -0.0000

Data Index: 396361 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.2788. Min Act: -0.0000

Data Index: 1293095 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.2519. Min Act: -0.0000

Data Index: 847800 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 3.6354. Min Range: -3.6354

Max Act: 1.9941. Min Act: -0.0000

Data Index: 49967 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.0355. Min Act: -0.0000

Data Index: 214888 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.0246. Min Act: -0.0000

Data Index: 1122862 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.0214. Min Act: -0.0000

Data Index: 761481 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.0335. Min Act: -0.0000

Data Index: 1238162 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.0044. Min Act: -0.0000

Data Index: 1471084 (Python Code)

Max Activating Token Index: 777

Text #18

Max Range: 3.6354. Min Range: -3.6354

Max Act: 2.1051. Min Act: -0.0000

Data Index: 1299770 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 3.6354. Min Range: -3.6354

Max Act: 1.9947. Min Act: -0.0000

Data Index: 25848 (C4 (Web Text))

Max Activating Token Index: 339