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

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

Neuron 826 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.4479. Min Act: -0.0000

Data Index: 1570474 (Python Code)

Max Activating Token Index: 545

Text #1

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1549696 (Python Code)

Max Activating Token Index: 305

Text #2

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1487290 (Python Code)

Max Activating Token Index: 174

Text #3

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3950. Min Act: -0.0000

Data Index: 409129 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1439820 (Python Code)

Max Activating Token Index: 790

Text #5

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1644617 (Python Code)

Max Activating Token Index: 750

Text #6

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3436. Min Act: -0.0000

Data Index: 1609643 (Python Code)

Max Activating Token Index: 920

Text #7

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1631244 (Python Code)

Max Activating Token Index: 235

Text #8

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1474871 (Python Code)

Max Activating Token Index: 807

Text #9

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1653678 (Python Code)

Max Activating Token Index: 508

Text #10

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1537643 (Python Code)

Max Activating Token Index: 584

Text #11

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3403. Min Act: -0.0000

Data Index: 772233 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1443542 (Python Code)

Max Activating Token Index: 80

Text #13

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1384115 (Python Code)

Max Activating Token Index: 326

Text #14

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1364358 (Python Code)

Max Activating Token Index: 634

Text #15

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.2912. Min Act: -0.0000

Data Index: 870564 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3059. Min Act: -0.0000

Data Index: 333278 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1461239 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.2974. Min Act: -0.0000

Data Index: 743529 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.2803. Min Act: -0.0000

Data Index: 440926 (C4 (Web Text))

Max Activating Token Index: 479