Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2957 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.4604. Min Act: -0.0000

Data Index: 1261037 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1476150 (Python Code)

Max Activating Token Index: 74

Text #2

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1485552 (Python Code)

Max Activating Token Index: 959

Text #3

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.9750. Min Act: -0.0000

Data Index: 638267 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.0065. Min Act: -0.0000

Data Index: 746904 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.9991. Min Act: -0.0000

Data Index: 387691 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.9374. Min Act: -0.0000

Data Index: 647990 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1537766 (Python Code)

Max Activating Token Index: 144

Text #8

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.9186. Min Act: -0.0000

Data Index: 840350 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.8579. Min Act: -0.0000

Data Index: 650040 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.9368. Min Act: -0.0000

Data Index: 849946 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.8465. Min Act: -0.0000

Data Index: 528746 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.8879. Min Act: -0.0000

Data Index: 46025 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.9085. Min Act: -0.0000

Data Index: 521684 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1612434 (Python Code)

Max Activating Token Index: 277

Text #15

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.7760. Min Act: -0.0000

Data Index: 341031 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1106395 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.8929. Min Act: -0.0000

Data Index: 20423 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.8528. Min Act: -0.0000

Data Index: 1510174 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 1.4604. Min Range: -1.4604

Max Act: 0.7344. Min Act: -0.0000

Data Index: 1399105 (Python Code)

Max Activating Token Index: 746