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

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

Neuron 618 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: 0.0287. Min Range: -0.0287

Max Act: 0.0287. Min Act: -0.0001

Data Index: 207371 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1288714 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0281. Min Act: -0.0001

Data Index: 348339 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0284. Min Act: -0.0001

Data Index: 1066544 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1555840 (Python Code)

Max Activating Token Index: 175

Text #5

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0279. Min Act: -0.0001

Data Index: 289229 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0280. Min Act: -0.0001

Data Index: 327816 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1177244 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0278. Min Act: -0.0001

Data Index: 656600 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0276. Min Act: -0.0001

Data Index: 268744 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0275. Min Act: -0.0001

Data Index: 1541037 (Python Code)

Max Activating Token Index: 268

Text #11

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0273. Min Act: -0.0001

Data Index: 529403 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0276. Min Act: -0.0001

Data Index: 461668 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0274. Min Act: -0.0001

Data Index: 121565 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0272. Min Act: -0.0001

Data Index: 821821 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1307993 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0273. Min Act: -0.0001

Data Index: 595079 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0267. Min Act: -0.0001

Data Index: 562043 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0268. Min Act: -0.0001

Data Index: 565882 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0270. Min Act: -0.0001

Data Index: 864859 (C4 (Web Text))

Max Activating Token Index: 191