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

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

Neuron 304 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0004

Data Index: 997989 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1436. Min Act: -0.0003

Data Index: 992588 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1420. Min Act: -0.0003

Data Index: 557094 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1484. Min Act: -0.0003

Data Index: 92846 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1429. Min Act: -0.0003

Data Index: 705578 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1371. Min Act: -0.0003

Data Index: 529575 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1357. Min Act: -0.0003

Data Index: 129477 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1314. Min Act: -0.0003

Data Index: 1027345 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1407. Min Act: -0.0004

Data Index: 1022994 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1349. Min Act: -0.0003

Data Index: 824455 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1294. Min Act: -0.0002

Data Index: 46287 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1360. Min Act: -0.0003

Data Index: 1236758 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1325. Min Act: -0.0003

Data Index: 753042 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1313. Min Act: -0.0003

Data Index: 41355 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1255. Min Act: -0.0003

Data Index: 796091 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1313. Min Act: -0.0003

Data Index: 972575 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1280. Min Act: -0.0003

Data Index: 1046515 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1262. Min Act: -0.0003

Data Index: 54764 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1322. Min Act: -0.0003

Data Index: 112580 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1279. Min Act: -0.0003

Data Index: 374818 (C4 (Web Text))

Max Activating Token Index: 695