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

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

Neuron 1457 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: 0.0290. Min Range: -0.0290

Max Act: 0.0283. Min Act: -0.0006

Data Index: 383928 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0289. Min Act: -0.0006

Data Index: 535443 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1293587 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0290. Min Act: -0.0006

Data Index: 522015 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0284. Min Act: -0.0006

Data Index: 149811 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0277. Min Act: -0.0006

Data Index: 599986 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0271. Min Act: -0.0006

Data Index: 913845 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0270. Min Act: -0.0006

Data Index: 605670 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0274. Min Act: -0.0006

Data Index: 709407 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0266. Min Act: -0.0006

Data Index: 82068 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0266. Min Act: -0.0006

Data Index: 195023 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1354180 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0269. Min Act: -0.0005

Data Index: 475622 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1305001 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1298619 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0262. Min Act: -0.0006

Data Index: 996582 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0267. Min Act: -0.0006

Data Index: 9098 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0261. Min Act: -0.0006

Data Index: 667650 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0260. Min Act: -0.0006

Data Index: 416893 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0260. Min Act: -0.0006

Data Index: 860062 (C4 (Web Text))

Max Activating Token Index: 127