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

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

Neuron 5714 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8763. Min Act: -0.0002

Data Index: 1249378 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.9099. Min Act: -0.0002

Data Index: 827141 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8680. Min Act: -0.0002

Data Index: 660650 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8530. Min Act: -0.0002

Data Index: 232506 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8408. Min Act: -0.0002

Data Index: 216802 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8486. Min Act: -0.0002

Data Index: 228923 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8305. Min Act: -0.0002

Data Index: 520346 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8209. Min Act: -0.0002

Data Index: 251807 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8260. Min Act: -0.0002

Data Index: 1282534 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8244. Min Act: -0.0002

Data Index: 525595 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8292. Min Act: -0.0002

Data Index: 994518 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8272. Min Act: -0.0002

Data Index: 509790 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8150. Min Act: -0.0002

Data Index: 614115 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8195. Min Act: -0.0002

Data Index: 1399001 (Python Code)

Max Activating Token Index: 390

Text #14

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8003. Min Act: -0.0002

Data Index: 1541199 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8001. Min Act: -0.0002

Data Index: 460924 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.7876. Min Act: -0.0002

Data Index: 485617 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.7851. Min Act: -0.0002

Data Index: 534339 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.7942. Min Act: -0.0002

Data Index: 664854 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.7972. Min Act: -0.0002

Data Index: 191964 (C4 (Web Text))

Max Activating Token Index: 302