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

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

Neuron 2113 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.8931. Min Act: -0.0000

Data Index: 705419 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.9339. Min Act: -0.0000

Data Index: 292942 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.9354. Min Act: -0.0000

Data Index: 456180 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 4.2528. Min Range: -4.2528

Max Act: 4.2528. Min Act: -0.0000

Data Index: 1247322 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.9141. Min Act: -0.0000

Data Index: 275951 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.8599. Min Act: -0.0000

Data Index: 128062 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.6866. Min Act: -0.0000

Data Index: 642067 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.4847. Min Act: 0.0000

Data Index: 282577 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.6329. Min Act: -0.0000

Data Index: 1259995 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.9050. Min Act: -0.0000

Data Index: 1354761 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.5725. Min Act: -0.0000

Data Index: 316315 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.5418. Min Act: -0.0000

Data Index: 421863 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.2628. Min Act: -0.0000

Data Index: 911748 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.3087. Min Act: -0.0000

Data Index: 216060 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.4036. Min Act: -0.0000

Data Index: 1303088 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.4218. Min Act: -0.0000

Data Index: 440682 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.3849. Min Act: -0.0000

Data Index: 620451 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.2380. Min Act: -0.0000

Data Index: 134902 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.3348. Min Act: -0.0000

Data Index: 47323 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 4.2528. Min Range: -4.2528

Max Act: 3.1345. Min Act: -0.0000

Data Index: 100515 (C4 (Web Text))

Max Activating Token Index: 712