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

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

Neuron 1922 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: 0.8906. Min Range: -0.8906

Max Act: 0.8906. Min Act: -0.0001

Data Index: 562274 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7637. Min Act: -0.0001

Data Index: 1004939 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7643. Min Act: -0.0001

Data Index: 354681 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7036. Min Act: -0.0001

Data Index: 343878 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7304. Min Act: -0.0001

Data Index: 822807 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8001. Min Act: -0.0001

Data Index: 114392 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7726. Min Act: -0.0001

Data Index: 1076862 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7459. Min Act: -0.0001

Data Index: 543960 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7457. Min Act: -0.0001

Data Index: 774486 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1003289 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7834. Min Act: -0.0001

Data Index: 224525 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7533. Min Act: -0.0001

Data Index: 934434 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7771. Min Act: -0.0001

Data Index: 542326 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7389. Min Act: -0.0001

Data Index: 772652 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7394. Min Act: -0.0001

Data Index: 1280252 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7409. Min Act: -0.0001

Data Index: 443549 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7181. Min Act: -0.0001

Data Index: 322675 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7287. Min Act: -0.0001

Data Index: 548479 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7471. Min Act: -0.0001

Data Index: 524340 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7458. Min Act: -0.0001

Data Index: 1104353 (C4 (Web Text))

Max Activating Token Index: 420