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

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

Neuron 2318 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.5592. Min Act: -0.0001

Data Index: 1615588 (Python Code)

Max Activating Token Index: 341

Text #1

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.5405. Min Act: -0.0001

Data Index: 1522133 (Python Code)

Max Activating Token Index: 737

Text #2

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.5020. Min Act: -0.0001

Data Index: 1625422 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.5089. Min Act: -0.0001

Data Index: 1616444 (Python Code)

Max Activating Token Index: 942

Text #4

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.4712. Min Act: -0.0001

Data Index: 1461483 (Python Code)

Max Activating Token Index: 809

Text #5

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.4572. Min Act: -0.0001

Data Index: 1557691 (Python Code)

Max Activating Token Index: 215

Text #6

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.4137. Min Act: -0.0001

Data Index: 516016 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.4146. Min Act: -0.0001

Data Index: 1357705 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3998. Min Act: -0.0001

Data Index: 934147 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3852. Min Act: -0.0001

Data Index: 661735 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.4083. Min Act: -0.0001

Data Index: 1552788 (Python Code)

Max Activating Token Index: 913

Text #11

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.4577. Min Act: -0.0001

Data Index: 1498888 (Python Code)

Max Activating Token Index: 147

Text #12

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.4114. Min Act: -0.0001

Data Index: 1394506 (Python Code)

Max Activating Token Index: 998

Text #13

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.4200. Min Act: -0.0001

Data Index: 1474713 (Python Code)

Max Activating Token Index: 1000

Text #14

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.4218. Min Act: -0.0001

Data Index: 1547990 (Python Code)

Max Activating Token Index: 811

Text #15

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3664. Min Act: -0.0001

Data Index: 910367 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.4313. Min Act: -0.0001

Data Index: 712269 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.4041. Min Act: -0.0001

Data Index: 1478599 (Python Code)

Max Activating Token Index: 82

Text #18

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3770. Min Act: -0.0001

Data Index: 1563751 (Python Code)

Max Activating Token Index: 626

Text #19

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3437. Min Act: -0.0001

Data Index: 1511350 (Python Code)

Max Activating Token Index: 701