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

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

Neuron 2788 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0618. Min Act: -0.0001

Data Index: 812789 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1353210 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0487. Min Act: -0.0000

Data Index: 381891 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0409. Min Act: -0.0000

Data Index: 68431 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0373. Min Act: -0.0000

Data Index: 104921 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0384. Min Act: -0.0000

Data Index: 61114 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0366. Min Act: -0.0001

Data Index: 901160 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1277809 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0370. Min Act: -0.0001

Data Index: 507730 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0363. Min Act: -0.0000

Data Index: 271228 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0347. Min Act: -0.0000

Data Index: 670409 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0349. Min Act: -0.0000

Data Index: 737964 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0350. Min Act: -0.0000

Data Index: 10117 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0329. Min Act: -0.0000

Data Index: 66631 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0324. Min Act: -0.0000

Data Index: 646252 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0315. Min Act: -0.0001

Data Index: 881153 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0312. Min Act: -0.0000

Data Index: 448760 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0322. Min Act: -0.0000

Data Index: 730079 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0305. Min Act: -0.0000

Data Index: 1179489 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0333. Min Act: -0.0001

Data Index: 887775 (C4 (Web Text))

Max Activating Token Index: 927