Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 201 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0003

Data Index: 20623 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1364610 (Python Code)

Max Activating Token Index: 893

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0271. Min Act: -0.0003

Data Index: 457372 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0266. Min Act: -0.0003

Data Index: 694682 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1266349 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1202688 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0254. Min Act: -0.0003

Data Index: 439893 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0250. Min Act: -0.0003

Data Index: 93152 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0245. Min Act: -0.0003

Data Index: 304130 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0248. Min Act: -0.0003

Data Index: 905453 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0247. Min Act: -0.0003

Data Index: 131714 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0248. Min Act: -0.0003

Data Index: 73479 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1067006 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0242. Min Act: -0.0003

Data Index: 963607 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0241. Min Act: -0.0003

Data Index: 248400 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0240. Min Act: -0.0003

Data Index: 235257 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0238. Min Act: -0.0003

Data Index: 557622 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0238. Min Act: -0.0003

Data Index: 715058 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0236. Min Act: -0.0003

Data Index: 363226 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1308042 (C4 (Web Text))

Max Activating Token Index: 371