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

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

Neuron 2607 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.8264. Min Act: -0.0001

Data Index: 933026 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.1096. Min Act: -0.0000

Data Index: 488681 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.9694. Min Act: -0.0001

Data Index: 733768 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.0003. Min Act: -0.0000

Data Index: 122308 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.9645. Min Act: -0.0001

Data Index: 527500 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.8236. Min Act: -0.0001

Data Index: 786662 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.8425. Min Act: -0.0000

Data Index: 374475 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.8298. Min Act: -0.0001

Data Index: 259188 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.8377. Min Act: -0.0001

Data Index: 549862 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.7556. Min Act: -0.0001

Data Index: 65366 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.7518. Min Act: -0.0001

Data Index: 1185911 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.8549. Min Act: -0.0001

Data Index: 755245 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.7748. Min Act: -0.0001

Data Index: 1013991 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.7400. Min Act: -0.0001

Data Index: 171768 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.7342. Min Act: -0.0001

Data Index: 778762 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.7528. Min Act: -0.0000

Data Index: 497117 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.7634. Min Act: -0.0001

Data Index: 803755 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.7687. Min Act: -0.0001

Data Index: 661891 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.7624. Min Act: -0.0000

Data Index: 459029 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 1.8264. Min Range: -1.8264

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1015538 (C4 (Web Text))

Max Activating Token Index: 210