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

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

Neuron 722 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7675. Min Range: -4.7675

Max Act: 4.7675. Min Act: -0.0000

Data Index: 235100 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 4.7675. Min Range: -4.7675

Max Act: 4.5315. Min Act: -0.0000

Data Index: 850064 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.8511. Min Act: -0.0000

Data Index: 1323673 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 4.7675. Min Range: -4.7675

Max Act: 4.2525. Min Act: -0.0000

Data Index: 797982 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 4.7675. Min Range: -4.7675

Max Act: 4.1440. Min Act: -0.0000

Data Index: 299458 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.9215. Min Act: -0.0000

Data Index: 1124258 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.7523. Min Act: -0.0000

Data Index: 888501 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.8676. Min Act: -0.0000

Data Index: 644244 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.9373. Min Act: -0.0000

Data Index: 780556 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.7081. Min Act: -0.0000

Data Index: 1137847 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.3306. Min Act: -0.0000

Data Index: 71620 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.6261. Min Act: -0.0000

Data Index: 1339411 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.7732. Min Act: -0.0000

Data Index: 567248 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.6170. Min Act: -0.0000

Data Index: 194352 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.7412. Min Act: -0.0000

Data Index: 1188178 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.5693. Min Act: -0.0000

Data Index: 836586 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.7915. Min Act: -0.0000

Data Index: 23631 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.2522. Min Act: -0.0000

Data Index: 522446 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.3795. Min Act: -0.0000

Data Index: 470927 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 4.7675. Min Range: -4.7675

Max Act: 3.2305. Min Act: -0.0000

Data Index: 618806 (C4 (Web Text))

Max Activating Token Index: 946