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

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

Neuron 3929 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: 4.7218. Min Range: -4.7218

Max Act: 4.7218. Min Act: -0.0000

Data Index: 526680 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 4.7218. Min Range: -4.7218

Max Act: 4.3140. Min Act: -0.0000

Data Index: 417780 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 4.7218. Min Range: -4.7218

Max Act: 4.1550. Min Act: -0.0000

Data Index: 259881 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 4.7218. Min Range: -4.7218

Max Act: 3.5808. Min Act: -0.0000

Data Index: 756543 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 4.7218. Min Range: -4.7218

Max Act: 4.0341. Min Act: -0.0000

Data Index: 879829 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 4.7218. Min Range: -4.7218

Max Act: 3.6278. Min Act: -0.0000

Data Index: 1231165 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 4.7218. Min Range: -4.7218

Max Act: 3.6925. Min Act: -0.0000

Data Index: 1076259 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 4.7218. Min Range: -4.7218

Max Act: 3.4579. Min Act: -0.0000

Data Index: 395900 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 4.7218. Min Range: -4.7218

Max Act: 3.2415. Min Act: -0.0000

Data Index: 635323 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 4.7218. Min Range: -4.7218

Max Act: 2.3277. Min Act: -0.0000

Data Index: 389231 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 4.7218. Min Range: -4.7218

Max Act: 2.9840. Min Act: -0.0000

Data Index: 662149 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 4.7218. Min Range: -4.7218

Max Act: 2.6047. Min Act: -0.0001

Data Index: 606271 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 4.7218. Min Range: -4.7218

Max Act: 2.9124. Min Act: -0.0000

Data Index: 45358 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 4.7218. Min Range: -4.7218

Max Act: 2.8365. Min Act: -0.0001

Data Index: 13850 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 4.7218. Min Range: -4.7218

Max Act: 2.0563. Min Act: -0.0000

Data Index: 61996 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 4.7218. Min Range: -4.7218

Max Act: 2.2848. Min Act: -0.0001

Data Index: 688962 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 4.7218. Min Range: -4.7218

Max Act: 2.4978. Min Act: -0.0000

Data Index: 85396 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 4.7218. Min Range: -4.7218

Max Act: 2.4493. Min Act: -0.0000

Data Index: 236751 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 4.7218. Min Range: -4.7218

Max Act: 2.6972. Min Act: -0.0000

Data Index: 1262021 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 4.7218. Min Range: -4.7218

Max Act: 2.8006. Min Act: -0.0000

Data Index: 146288 (C4 (Web Text))

Max Activating Token Index: 67