Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1503 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.3365. Min Act: -0.0001

Data Index: 262434 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2838. Min Act: -0.0001

Data Index: 1523264 (Python Code)

Max Activating Token Index: 98

Text #2

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.3221. Min Act: -0.0001

Data Index: 1131466 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0099. Min Act: -0.0001

Data Index: 57706 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0565. Min Act: -0.0001

Data Index: 967773 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.9200. Min Act: -0.0001

Data Index: 964455 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0347. Min Act: -0.0001

Data Index: 1376734 (Python Code)

Max Activating Token Index: 121

Text #7

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.9741. Min Act: -0.0002

Data Index: 926229 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0411. Min Act: -0.0001

Data Index: 793168 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0141. Min Act: -0.0001

Data Index: 664877 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.9138. Min Act: -0.0001

Data Index: 1025956 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.8870. Min Act: -0.0001

Data Index: 1093032 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.9851. Min Act: -0.0001

Data Index: 669936 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.8420. Min Act: -0.0001

Data Index: 158082 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.9498. Min Act: -0.0002

Data Index: 531188 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0204. Min Act: -0.0001

Data Index: 682121 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.8896. Min Act: -0.0001

Data Index: 703383 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.8284. Min Act: -0.0001

Data Index: 656362 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.8700. Min Act: -0.0001

Data Index: 771504 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 1.3365. Min Range: -1.3365

Max Act: 0.9270. Min Act: -0.0002

Data Index: 1196171 (C4 (Web Text))

Max Activating Token Index: 485