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

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

Neuron 2639 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: 4.3039. Min Range: -4.3039

Max Act: 3.8862. Min Act: -0.0000

Data Index: 1521361 (Python Code)

Max Activating Token Index: 650

Text #1

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.8160. Min Act: -0.0000

Data Index: 107797 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 4.3039. Min Range: -4.3039

Max Act: 4.3039. Min Act: -0.0000

Data Index: 119250 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.7952. Min Act: -0.0000

Data Index: 851093 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.1760. Min Act: -0.0000

Data Index: 81571 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.6149. Min Act: -0.0000

Data Index: 1126319 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.4394. Min Act: -0.0000

Data Index: 300124 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.4907. Min Act: -0.0000

Data Index: 1242361 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.4102. Min Act: -0.0000

Data Index: 698068 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.0912. Min Act: -0.0000

Data Index: 946461 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.3744. Min Act: -0.0000

Data Index: 1150057 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.1141. Min Act: -0.0000

Data Index: 190592 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.0925. Min Act: -0.0000

Data Index: 342987 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.5515. Min Act: -0.0000

Data Index: 136169 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.3537. Min Act: -0.0000

Data Index: 1157347 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.0694. Min Act: -0.0000

Data Index: 284072 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.1860. Min Act: -0.0000

Data Index: 765015 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 4.3039. Min Range: -4.3039

Max Act: 2.9239. Min Act: -0.0000

Data Index: 907027 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 4.3039. Min Range: -4.3039

Max Act: 2.7540. Min Act: -0.0000

Data Index: 1145387 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 4.3039. Min Range: -4.3039

Max Act: 3.0110. Min Act: -0.0000

Data Index: 300584 (C4 (Web Text))

Max Activating Token Index: 18