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

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

Neuron 6046 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.7345. Min Act: 0.0000

Data Index: 1425977 (Python Code)

Max Activating Token Index: 336

Text #1

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1391245 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1610997 (Python Code)

Max Activating Token Index: 279

Text #3

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.6325. Min Act: -0.0000

Data Index: 1538297 (Python Code)

Max Activating Token Index: 457

Text #4

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1612857 (Python Code)

Max Activating Token Index: 269

Text #5

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1480734 (Python Code)

Max Activating Token Index: 260

Text #6

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.6177. Min Act: -0.0000

Data Index: 529215 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1540402 (Python Code)

Max Activating Token Index: 568

Text #8

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5977. Min Act: 0.0000

Data Index: 10791 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1042575 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1401190 (Python Code)

Max Activating Token Index: 158

Text #11

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5310. Min Act: 0.0000

Data Index: 1564937 (Python Code)

Max Activating Token Index: 645

Text #12

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5558. Min Act: 0.0000

Data Index: 835863 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1517274 (Python Code)

Max Activating Token Index: 921

Text #14

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5348. Min Act: -0.0000

Data Index: 1576316 (Python Code)

Max Activating Token Index: 130

Text #15

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1563869 (Python Code)

Max Activating Token Index: 457

Text #16

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1584781 (Python Code)

Max Activating Token Index: 953

Text #17

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1480976 (Python Code)

Max Activating Token Index: 97

Text #18

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5225. Min Act: 0.0000

Data Index: 481931 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5110. Min Act: -0.0000

Data Index: 829365 (C4 (Web Text))

Max Activating Token Index: 600