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

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

Neuron 4746 in Layer 0

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: 0.0299. Min Range: -0.0299

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1585875 (Python Code)

Max Activating Token Index: 34

Text #1

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1514596 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0261. Min Act: -0.0001

Data Index: 1345046 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0258. Min Act: -0.0001

Data Index: 1207500 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0249. Min Act: -0.0001

Data Index: 334457 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0245. Min Act: -0.0001

Data Index: 295648 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0244. Min Act: -0.0001

Data Index: 119882 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1645876 (Python Code)

Max Activating Token Index: 546

Text #8

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0243. Min Act: -0.0001

Data Index: 536498 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0237. Min Act: -0.0001

Data Index: 1369975 (Python Code)

Max Activating Token Index: 839

Text #10

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0231. Min Act: -0.0001

Data Index: 1512031 (Python Code)

Max Activating Token Index: 562

Text #11

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0231. Min Act: -0.0001

Data Index: 1306776 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0233. Min Act: -0.0001

Data Index: 564965 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0232. Min Act: -0.0001

Data Index: 788577 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0229. Min Act: -0.0001

Data Index: 1460412 (Python Code)

Max Activating Token Index: 805

Text #15

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0224. Min Act: -0.0001

Data Index: 1480289 (Python Code)

Max Activating Token Index: 300

Text #16

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1018665 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0220. Min Act: -0.0001

Data Index: 1432506 (Python Code)

Max Activating Token Index: 172

Text #18

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0224. Min Act: -0.0001

Data Index: 1492279 (Python Code)

Max Activating Token Index: 142

Text #19

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1490312 (Python Code)

Max Activating Token Index: 294