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

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

Neuron 5251 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0544. Min Act: -0.0001

Data Index: 394935 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0554. Min Act: -0.0001

Data Index: 199213 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0407. Min Act: -0.0001

Data Index: 723792 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0457. Min Act: -0.0001

Data Index: 584584 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0453. Min Act: -0.0001

Data Index: 675354 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0432. Min Act: -0.0001

Data Index: 162158 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1259083 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0399. Min Act: -0.0002

Data Index: 886641 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1027170 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1181963 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0344. Min Act: -0.0001

Data Index: 447682 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0363. Min Act: -0.0002

Data Index: 148579 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0325. Min Act: -0.0001

Data Index: 1445048 (Python Code)

Max Activating Token Index: 821

Text #13

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1049402 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0309. Min Act: -0.0001

Data Index: 431658 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0348. Min Act: -0.0001

Data Index: 320837 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0351. Min Act: -0.0002

Data Index: 28221 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0331. Min Act: -0.0001

Data Index: 680887 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0325. Min Act: -0.0001

Data Index: 871000 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1252723 (C4 (Web Text))

Max Activating Token Index: 29