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

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

Neuron 3144 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0321. Min Range: -4.0321

Max Act: 4.0321. Min Act: -0.0001

Data Index: 1045080 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.2492. Min Act: -0.0000

Data Index: 598376 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.1479. Min Act: -0.0001

Data Index: 713090 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.0351. Min Act: -0.0000

Data Index: 446879 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.5067. Min Act: -0.0000

Data Index: 1172384 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.0070. Min Act: -0.0001

Data Index: 855132 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.7963. Min Act: -0.0001

Data Index: 1248247 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.6304. Min Act: -0.0000

Data Index: 406556 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.6982. Min Act: -0.0001

Data Index: 725660 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.5842. Min Act: -0.0000

Data Index: 419780 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.5834. Min Act: -0.0001

Data Index: 1004850 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.7087. Min Act: -0.0001

Data Index: 956413 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.4279. Min Act: -0.0001

Data Index: 635934 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.3518. Min Act: -0.0001

Data Index: 306263 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.4188. Min Act: -0.0000

Data Index: 531940 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.5584. Min Act: -0.0001

Data Index: 360303 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.3998. Min Act: -0.0000

Data Index: 443163 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.4017. Min Act: -0.0001

Data Index: 1094401 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.3777. Min Act: -0.0000

Data Index: 518221 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 4.0321. Min Range: -4.0321

Max Act: 2.3764. Min Act: -0.0001

Data Index: 1014852 (C4 (Web Text))

Max Activating Token Index: 161