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

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

Neuron 2533 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.7141. Min Act: -0.0000

Data Index: 392378 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.7295. Min Act: -0.0001

Data Index: 694377 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.6725. Min Act: -0.0001

Data Index: 1649845 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1191355 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5974. Min Act: -0.0001

Data Index: 792665 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5845. Min Act: -0.0001

Data Index: 1375815 (Python Code)

Max Activating Token Index: 652

Text #6

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5875. Min Act: -0.0001

Data Index: 1653274 (Python Code)

Max Activating Token Index: 1011

Text #7

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5682. Min Act: -0.0000

Data Index: 1222278 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5523. Min Act: -0.0001

Data Index: 786792 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5675. Min Act: -0.0000

Data Index: 601766 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5590. Min Act: -0.0000

Data Index: 743984 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1120474 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5346. Min Act: -0.0000

Data Index: 161462 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5495. Min Act: -0.0000

Data Index: 876025 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5337. Min Act: -0.0000

Data Index: 709845 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5465. Min Act: -0.0000

Data Index: 210191 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1291469 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5265. Min Act: -0.0000

Data Index: 537252 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5419. Min Act: -0.0000

Data Index: 623380 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5606. Min Act: -0.0000

Data Index: 273343 (C4 (Web Text))

Max Activating Token Index: 793