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

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

Neuron 5883 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.8456. Min Act: -0.0000

Data Index: 303792 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1349186 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.7342. Min Act: -0.0000

Data Index: 131110 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6281. Min Act: -0.0000

Data Index: 916834 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6837. Min Act: -0.0000

Data Index: 697364 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6122. Min Act: -0.0000

Data Index: 720227 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6056. Min Act: -0.0000

Data Index: 794687 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1101243 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6503. Min Act: -0.0000

Data Index: 306510 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1320413 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5595. Min Act: -0.0000

Data Index: 972755 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1058801 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5666. Min Act: -0.0000

Data Index: 226935 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1359661 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1011293 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5544. Min Act: -0.0000

Data Index: 616947 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5652. Min Act: -0.0000

Data Index: 605335 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5557. Min Act: -0.0000

Data Index: 645394 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5344. Min Act: -0.0000

Data Index: 181661 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.8456. Min Range: -0.8456

Max Act: 0.5136. Min Act: -0.0000

Data Index: 4908 (C4 (Web Text))

Max Activating Token Index: 447