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

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

Neuron 3884 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2898. Min Range: -1.2898

Max Act: 1.2898. Min Act: -0.0000

Data Index: 1292142 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 1.2898. Min Range: -1.2898

Max Act: 1.0194. Min Act: -0.0000

Data Index: 189716 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.9433. Min Act: -0.0000

Data Index: 552754 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1159621 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.9674. Min Act: -0.0000

Data Index: 1343892 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.8119. Min Act: -0.0000

Data Index: 401888 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.7867. Min Act: -0.0000

Data Index: 591774 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.9552. Min Act: -0.0000

Data Index: 805056 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.8999. Min Act: -0.0000

Data Index: 522581 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.9761. Min Act: -0.0000

Data Index: 904122 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.7641. Min Act: -0.0000

Data Index: 661163 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.6717. Min Act: -0.0000

Data Index: 746546 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.7880. Min Act: -0.0000

Data Index: 296389 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.7869. Min Act: -0.0000

Data Index: 141123 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1252239 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.7604. Min Act: -0.0000

Data Index: 828517 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.7546. Min Act: -0.0000

Data Index: 990179 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1278221 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.7730. Min Act: -0.0000

Data Index: 455604 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 1.2898. Min Range: -1.2898

Max Act: 0.7024. Min Act: -0.0000

Data Index: 178559 (C4 (Web Text))

Max Activating Token Index: 484