Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1165 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0336. Min Act: -0.0005

Data Index: 595841 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0335. Min Act: -0.0005

Data Index: 471347 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0338. Min Act: -0.0005

Data Index: 859280 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0328. Min Act: -0.0005

Data Index: 260534 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0295. Min Act: -0.0005

Data Index: 71268 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0307. Min Act: -0.0005

Data Index: 1335451 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0302. Min Act: -0.0005

Data Index: 606512 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0308. Min Act: -0.0005

Data Index: 56792 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0299. Min Act: -0.0005

Data Index: 694138 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0299. Min Act: -0.0005

Data Index: 305290 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0280. Min Act: -0.0005

Data Index: 169567 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0282. Min Act: -0.0005

Data Index: 585531 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0287. Min Act: -0.0005

Data Index: 764650 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0286. Min Act: -0.0005

Data Index: 285291 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0283. Min Act: -0.0005

Data Index: 1004764 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0281. Min Act: -0.0005

Data Index: 1015380 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0292. Min Act: -0.0005

Data Index: 502335 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0280. Min Act: -0.0005

Data Index: 687189 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0274. Min Act: -0.0005

Data Index: 1283845 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0281. Min Act: -0.0005

Data Index: 295152 (C4 (Web Text))

Max Activating Token Index: 244