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

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

Neuron 3747 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: 0.4958. Min Range: -0.4958

Max Act: 0.4958. Min Act: -0.0002

Data Index: 723310 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4713. Min Act: -0.0002

Data Index: 254381 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4678. Min Act: -0.0002

Data Index: 538852 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4570. Min Act: -0.0002

Data Index: 1236138 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4493. Min Act: -0.0002

Data Index: 1233261 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4518. Min Act: -0.0002

Data Index: 226025 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4435. Min Act: -0.0002

Data Index: 700232 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4507. Min Act: -0.0002

Data Index: 50407 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4420. Min Act: -0.0002

Data Index: 1022209 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4274. Min Act: -0.0002

Data Index: 590916 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4300. Min Act: -0.0002

Data Index: 158196 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4269. Min Act: -0.0002

Data Index: 195974 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4238. Min Act: -0.0002

Data Index: 148500 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4206. Min Act: -0.0002

Data Index: 87746 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4157. Min Act: -0.0002

Data Index: 273298 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4203. Min Act: -0.0002

Data Index: 531125 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4217. Min Act: -0.0002

Data Index: 209124 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4194. Min Act: -0.0002

Data Index: 1492093 (Python Code)

Max Activating Token Index: 314

Text #18

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4193. Min Act: -0.0002

Data Index: 45653 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4071. Min Act: -0.0002

Data Index: 799046 (C4 (Web Text))

Max Activating Token Index: 80