Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1429 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0006

Data Index: 1293718 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0311. Min Act: -0.0006

Data Index: 942431 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0307. Min Act: -0.0006

Data Index: 822890 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0287. Min Act: -0.0006

Data Index: 625216 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0281. Min Act: -0.0006

Data Index: 530512 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0296. Min Act: -0.0006

Data Index: 579636 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0287. Min Act: -0.0006

Data Index: 504226 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0258. Min Act: -0.0006

Data Index: 1077168 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0279. Min Act: -0.0006

Data Index: 398346 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0284. Min Act: -0.0006

Data Index: 825577 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0271. Min Act: -0.0006

Data Index: 519838 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0264. Min Act: -0.0006

Data Index: 17415 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0280. Min Act: -0.0006

Data Index: 612789 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0274. Min Act: -0.0006

Data Index: 1072946 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0268. Min Act: -0.0006

Data Index: 675017 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0270. Min Act: -0.0006

Data Index: 133563 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0264. Min Act: -0.0006

Data Index: 284762 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0276. Min Act: -0.0006

Data Index: 427467 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0269. Min Act: -0.0006

Data Index: 338412 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0268. Min Act: -0.0006

Data Index: 1211568 (C4 (Web Text))

Max Activating Token Index: 555