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

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

Neuron 6096 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0001

Data Index: 2721 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1119457 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0415. Min Act: -0.0001

Data Index: 26146 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0388. Min Act: -0.0001

Data Index: 846977 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0337. Min Act: -0.0001

Data Index: 913532 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0378. Min Act: -0.0001

Data Index: 295682 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0355. Min Act: -0.0001

Data Index: 818826 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0432. Min Act: -0.0001

Data Index: 826273 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0330. Min Act: -0.0001

Data Index: 885866 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0344. Min Act: -0.0001

Data Index: 191400 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0374. Min Act: -0.0001

Data Index: 751621 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1528485 (Python Code)

Max Activating Token Index: 489

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0353. Min Act: -0.0001

Data Index: 828652 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0365. Min Act: -0.0001

Data Index: 771167 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1098213 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0358. Min Act: -0.0001

Data Index: 737196 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1299882 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0370. Min Act: -0.0001

Data Index: 577236 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0324. Min Act: -0.0001

Data Index: 512617 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0354. Min Act: -0.0001

Data Index: 985445 (C4 (Web Text))

Max Activating Token Index: 6