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

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

Neuron 1503 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.8267. Min Act: -0.0000

Data Index: 491327 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.5961. Min Act: -0.0000

Data Index: 761501 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.6662. Min Act: -0.0001

Data Index: 1244423 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.6047. Min Act: -0.0000

Data Index: 1502514 (Python Code)

Max Activating Token Index: 118

Text #4

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.5444. Min Act: -0.0001

Data Index: 580151 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.3241. Min Act: -0.0000

Data Index: 1054716 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.3950. Min Act: -0.0000

Data Index: 492491 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.3864. Min Act: -0.0001

Data Index: 163894 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.3020. Min Act: -0.0001

Data Index: 1476032 (Python Code)

Max Activating Token Index: 80

Text #9

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.3286. Min Act: -0.0000

Data Index: 1504160 (Python Code)

Max Activating Token Index: 735

Text #10

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.2528. Min Act: -0.0001

Data Index: 351580 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.2360. Min Act: -0.0000

Data Index: 995836 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.3125. Min Act: -0.0001

Data Index: 611212 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.2774. Min Act: -0.0001

Data Index: 1561387 (Python Code)

Max Activating Token Index: 207

Text #14

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.2528. Min Act: -0.0001

Data Index: 800016 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.2771. Min Act: -0.0001

Data Index: 354958 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.2291. Min Act: -0.0001

Data Index: 878013 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.2501. Min Act: -0.0001

Data Index: 444417 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.1794. Min Act: -0.0000

Data Index: 1553121 (Python Code)

Max Activating Token Index: 1004

Text #19

Max Range: 1.8267. Min Range: -1.8267

Max Act: 1.2172. Min Act: -0.0001

Data Index: 882309 (C4 (Web Text))

Max Activating Token Index: 333