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

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

Neuron 3503 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.8586. Min Act: -0.0001

Data Index: 1426730 (Python Code)

Max Activating Token Index: 341

Text #1

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.8218. Min Act: -0.0001

Data Index: 1594673 (Python Code)

Max Activating Token Index: 1017

Text #2

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7680. Min Act: 0.0000

Data Index: 1409499 (Python Code)

Max Activating Token Index: 525

Text #3

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7237. Min Act: 0.0003

Data Index: 1387873 (Python Code)

Max Activating Token Index: 584

Text #4

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7230. Min Act: -0.0001

Data Index: 1476134 (Python Code)

Max Activating Token Index: 150

Text #5

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7180. Min Act: 0.0001

Data Index: 1444449 (Python Code)

Max Activating Token Index: 266

Text #6

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7131. Min Act: 0.0000

Data Index: 1572538 (Python Code)

Max Activating Token Index: 242

Text #7

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7319. Min Act: -0.0001

Data Index: 1443682 (Python Code)

Max Activating Token Index: 436

Text #8

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1539620 (Python Code)

Max Activating Token Index: 442

Text #9

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.6565. Min Act: -0.0001

Data Index: 1478248 (Python Code)

Max Activating Token Index: 47

Text #10

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1377181 (Python Code)

Max Activating Token Index: 50

Text #11

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.6540. Min Act: 0.0001

Data Index: 1644726 (Python Code)

Max Activating Token Index: 47

Text #12

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.6126. Min Act: 0.0000

Data Index: 1511367 (Python Code)

Max Activating Token Index: 328

Text #13

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.6292. Min Act: 0.0001

Data Index: 1573867 (Python Code)

Max Activating Token Index: 61

Text #14

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1640008 (Python Code)

Max Activating Token Index: 223

Text #15

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.6183. Min Act: 0.0001

Data Index: 1550103 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.5955. Min Act: 0.0000

Data Index: 1445913 (Python Code)

Max Activating Token Index: 439

Text #17

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1420740 (Python Code)

Max Activating Token Index: 695

Text #18

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1519833 (Python Code)

Max Activating Token Index: 175

Text #19

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1598742 (Python Code)

Max Activating Token Index: 1003