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

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

Neuron 2102 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.7534. Min Act: -0.0001

Data Index: 138375 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6350. Min Act: -0.0000

Data Index: 633338 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5845. Min Act: -0.0001

Data Index: 659550 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5614. Min Act: -0.0001

Data Index: 353903 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5431. Min Act: -0.0000

Data Index: 894800 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5748. Min Act: -0.0001

Data Index: 794172 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5894. Min Act: -0.0000

Data Index: 813646 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1422820 (Python Code)

Max Activating Token Index: 952

Text #8

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5079. Min Act: -0.0001

Data Index: 204517 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5272. Min Act: -0.0000

Data Index: 966328 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5317. Min Act: -0.0001

Data Index: 1134806 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1087156 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5443. Min Act: -0.0001

Data Index: 368851 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.4038. Min Act: -0.0000

Data Index: 37200 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1583461 (Python Code)

Max Activating Token Index: 616

Text #15

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.4429. Min Act: -0.0001

Data Index: 921920 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5273. Min Act: -0.0001

Data Index: 816021 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.4724. Min Act: -0.0001

Data Index: 1357363 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5326. Min Act: -0.0001

Data Index: 550043 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5131. Min Act: -0.0000

Data Index: 266178 (C4 (Web Text))

Max Activating Token Index: 295