Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3334 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3408. Min Range: -1.3408

Max Act: 1.2806. Min Act: -0.0000

Data Index: 176365 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 1.3408. Min Range: -1.3408

Max Act: 1.3044. Min Act: -0.0000

Data Index: 393879 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 1.3408. Min Range: -1.3408

Max Act: 1.3408. Min Act: -0.0000

Data Index: 191195 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 1.3408. Min Range: -1.3408

Max Act: 1.0905. Min Act: -0.0000

Data Index: 638543 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 1.3408. Min Range: -1.3408

Max Act: 1.1472. Min Act: -0.0000

Data Index: 341850 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 1.3408. Min Range: -1.3408

Max Act: 0.9867. Min Act: -0.0000

Data Index: 674947 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 1.3408. Min Range: -1.3408

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1311165 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 1.3408. Min Range: -1.3408

Max Act: 0.9785. Min Act: -0.0000

Data Index: 1143276 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 1.3408. Min Range: -1.3408

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1638732 (Python Code)

Max Activating Token Index: 418

Text #9

Max Range: 1.3408. Min Range: -1.3408

Max Act: 0.7369. Min Act: -0.0000

Data Index: 100815 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 1.3408. Min Range: -1.3408

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1504513 (Python Code)

Max Activating Token Index: 115

Text #11

Max Range: 1.3408. Min Range: -1.3408

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1466674 (Python Code)

Max Activating Token Index: 141

Text #12

Max Range: 1.3408. Min Range: -1.3408

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1376390 (Python Code)

Max Activating Token Index: 89

Text #13

Max Range: 1.3408. Min Range: -1.3408

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1478955 (Python Code)

Max Activating Token Index: 127

Text #14

Max Range: 1.3408. Min Range: -1.3408

Max Act: 0.6692. Min Act: -0.0000

Data Index: 36402 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 1.3408. Min Range: -1.3408

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1575678 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 1.3408. Min Range: -1.3408

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1442396 (Python Code)

Max Activating Token Index: 384

Text #17

Max Range: 1.3408. Min Range: -1.3408

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1456833 (Python Code)

Max Activating Token Index: 240

Text #18

Max Range: 1.3408. Min Range: -1.3408

Max Act: 0.5549. Min Act: -0.0000

Data Index: 937032 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 1.3408. Min Range: -1.3408

Max Act: 0.5969. Min Act: -0.0000

Data Index: 914357 (C4 (Web Text))

Max Activating Token Index: 126