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

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

Neuron 275 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0005

Data Index: 1214907 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0368. Min Act: -0.0006

Data Index: 991418 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0367. Min Act: -0.0005

Data Index: 733013 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0353. Min Act: -0.0006

Data Index: 1521031 (Python Code)

Max Activating Token Index: 931

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0352. Min Act: -0.0005

Data Index: 1031662 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0349. Min Act: -0.0005

Data Index: 205595 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0349. Min Act: -0.0005

Data Index: 744526 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0346. Min Act: -0.0005

Data Index: 949477 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0335. Min Act: -0.0006

Data Index: 1514683 (Python Code)

Max Activating Token Index: 899

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1462189 (Python Code)

Max Activating Token Index: 891

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0329. Min Act: -0.0005

Data Index: 307852 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0333. Min Act: -0.0005

Data Index: 922405 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0326. Min Act: -0.0005

Data Index: 870751 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1460660 (Python Code)

Max Activating Token Index: 578

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0324. Min Act: -0.0005

Data Index: 586756 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0322. Min Act: -0.0005

Data Index: 142979 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0321. Min Act: -0.0006

Data Index: 1481722 (Python Code)

Max Activating Token Index: 792

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0320. Min Act: -0.0005

Data Index: 324175 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0312. Min Act: -0.0005

Data Index: 469590 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0317. Min Act: -0.0005

Data Index: 663411 (C4 (Web Text))

Max Activating Token Index: 214