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

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

Neuron 37 in Layer 1

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: 0.0423. Min Range: -0.0423

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1130770 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0408. Min Act: -0.0002

Data Index: 995533 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0403. Min Act: -0.0002

Data Index: 292142 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1268177 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0386. Min Act: -0.0002

Data Index: 216685 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0384. Min Act: -0.0002

Data Index: 299674 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1133307 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1167823 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0366. Min Act: -0.0002

Data Index: 950304 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1131277 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0348. Min Act: -0.0002

Data Index: 235821 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0353. Min Act: -0.0002

Data Index: 74347 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1545586 (Python Code)

Max Activating Token Index: 245

Text #13

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1318409 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1179619 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0336. Min Act: -0.0002

Data Index: 357648 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0341. Min Act: -0.0002

Data Index: 625325 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0335. Min Act: -0.0002

Data Index: 504563 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1109243 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0329. Min Act: -0.0002

Data Index: 638167 (C4 (Web Text))

Max Activating Token Index: 679