Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4517 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0322. Min Act: -0.0002

Data Index: 706700 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0311. Min Act: -0.0002

Data Index: 786448 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0280. Min Act: -0.0002

Data Index: 487042 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1232153 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0310. Min Act: -0.0002

Data Index: 939875 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1232149 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0262. Min Act: -0.0002

Data Index: 858017 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1197680 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0262. Min Act: -0.0002

Data Index: 347214 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0261. Min Act: -0.0002

Data Index: 934773 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0257. Min Act: -0.0002

Data Index: 186860 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0254. Min Act: -0.0002

Data Index: 820723 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0259. Min Act: -0.0002

Data Index: 894053 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0250. Min Act: -0.0002

Data Index: 626810 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0253. Min Act: -0.0002

Data Index: 403858 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0246. Min Act: -0.0002

Data Index: 995048 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1042003 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0249. Min Act: -0.0002

Data Index: 653782 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0265. Min Act: -0.0002

Data Index: 840684 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0246. Min Act: -0.0002

Data Index: 101056 (C4 (Web Text))

Max Activating Token Index: 534