Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3678 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0512. Min Act: -0.0001

Data Index: 732219 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0498. Min Act: -0.0001

Data Index: 498283 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1160934 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0466. Min Act: -0.0001

Data Index: 174794 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0464. Min Act: -0.0001

Data Index: 884889 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0446. Min Act: -0.0001

Data Index: 368652 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0421. Min Act: -0.0001

Data Index: 478719 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0452. Min Act: -0.0001

Data Index: 451536 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0436. Min Act: -0.0001

Data Index: 792453 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0405. Min Act: -0.0001

Data Index: 475348 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1184540 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1223008 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0420. Min Act: -0.0001

Data Index: 33094 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0402. Min Act: -0.0001

Data Index: 903469 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0410. Min Act: -0.0001

Data Index: 121730 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0374. Min Act: -0.0001

Data Index: 436873 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0372. Min Act: -0.0001

Data Index: 46062 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1344112 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0371. Min Act: -0.0001

Data Index: 241944 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0354. Min Act: -0.0001

Data Index: 825265 (C4 (Web Text))

Max Activating Token Index: 541