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

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

Neuron 2284 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1579. Min Act: -0.0002

Data Index: 1529496 (Python Code)

Max Activating Token Index: 348

Text #1

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1440. Min Act: -0.0002

Data Index: 1577948 (Python Code)

Max Activating Token Index: 918

Text #2

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1380. Min Act: -0.0002

Data Index: 1506090 (Python Code)

Max Activating Token Index: 161

Text #3

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1329. Min Act: -0.0002

Data Index: 1175929 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1212. Min Act: -0.0002

Data Index: 777848 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1168. Min Act: -0.0002

Data Index: 1552629 (Python Code)

Max Activating Token Index: 812

Text #6

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1130. Min Act: -0.0002

Data Index: 1472180 (Python Code)

Max Activating Token Index: 120

Text #7

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1086. Min Act: -0.0002

Data Index: 1559893 (Python Code)

Max Activating Token Index: 919

Text #8

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1038. Min Act: -0.0002

Data Index: 583652 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1000. Min Act: -0.0002

Data Index: 571999 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.1005. Min Act: -0.0002

Data Index: 43571 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.0985. Min Act: -0.0002

Data Index: 687130 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.0977. Min Act: -0.0002

Data Index: 837525 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1631900 (Python Code)

Max Activating Token Index: 458

Text #14

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.0994. Min Act: -0.0002

Data Index: 897216 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.0959. Min Act: -0.0002

Data Index: 1624876 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.0994. Min Act: -0.0002

Data Index: 820398 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1493048 (Python Code)

Max Activating Token Index: 731

Text #18

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.0955. Min Act: -0.0002

Data Index: 336160 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.1579. Min Range: -0.1579

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1194659 (C4 (Web Text))

Max Activating Token Index: 443