Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1447 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1335. Min Range: -1.1335

Max Act: 1.1335. Min Act: -0.0000

Data Index: 269414 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 1.1335. Min Range: -1.1335

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1182075 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.9964. Min Act: -0.0000

Data Index: 895927 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1278757 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.9341. Min Act: -0.0000

Data Index: 634115 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.9491. Min Act: -0.0000

Data Index: 993174 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.9216. Min Act: -0.0000

Data Index: 732814 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.8396. Min Act: -0.0000

Data Index: 628951 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1270240 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1075113 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.8495. Min Act: -0.0000

Data Index: 785850 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.8603. Min Act: -0.0000

Data Index: 536140 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.8674. Min Act: -0.0000

Data Index: 135008 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1075157 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1354736 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1332235 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.7591. Min Act: -0.0000

Data Index: 188929 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.7786. Min Act: -0.0000

Data Index: 689973 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.8299. Min Act: -0.0000

Data Index: 489698 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 1.1335. Min Range: -1.1335

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1168196 (C4 (Web Text))

Max Activating Token Index: 192