Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 596 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0333. Min Act: -0.0002

Data Index: 285036 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1052321 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0335. Min Act: -0.0002

Data Index: 564739 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0318. Min Act: -0.0003

Data Index: 779819 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0323. Min Act: -0.0003

Data Index: 239639 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0335. Min Act: -0.0003

Data Index: 528772 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1332926 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0313. Min Act: -0.0003

Data Index: 817255 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1319459 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0317. Min Act: -0.0003

Data Index: 235725 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0311. Min Act: -0.0003

Data Index: 295354 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1269206 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0305. Min Act: -0.0003

Data Index: 14473 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0302. Min Act: -0.0003

Data Index: 522092 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1199104 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0292. Min Act: -0.0003

Data Index: 596603 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1358293 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1335926 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0290. Min Act: -0.0003

Data Index: 845325 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0290. Min Act: -0.0003

Data Index: 357835 (C4 (Web Text))

Max Activating Token Index: 593