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

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

Neuron 3251 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0545. Min Act: -0.0003

Data Index: 20466 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0561. Min Act: -0.0003

Data Index: 71909 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0488. Min Act: -0.0003

Data Index: 546752 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0466. Min Act: -0.0002

Data Index: 340765 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0450. Min Act: -0.0003

Data Index: 389626 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0430. Min Act: -0.0003

Data Index: 73424 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0454. Min Act: -0.0003

Data Index: 447169 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0460. Min Act: -0.0003

Data Index: 184939 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0460. Min Act: -0.0002

Data Index: 875028 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0446. Min Act: -0.0002

Data Index: 507773 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0451. Min Act: -0.0003

Data Index: 32913 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0436. Min Act: -0.0003

Data Index: 557790 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0434. Min Act: -0.0003

Data Index: 265476 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0422. Min Act: -0.0003

Data Index: 330134 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0414. Min Act: -0.0003

Data Index: 213113 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0425. Min Act: -0.0003

Data Index: 117976 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1064378 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1026188 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1299711 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0385. Min Act: -0.0003

Data Index: 605940 (C4 (Web Text))

Max Activating Token Index: 213