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

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

Neuron 4572 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0620. Min Act: -0.0000

Data Index: 68824 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0576. Min Act: -0.0000

Data Index: 1263818 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0479. Min Act: -0.0000

Data Index: 416743 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0474. Min Act: -0.0000

Data Index: 572033 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0435. Min Act: -0.0000

Data Index: 217017 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0480. Min Act: -0.0000

Data Index: 606491 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0456. Min Act: -0.0000

Data Index: 161477 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0420. Min Act: -0.0000

Data Index: 292274 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0432. Min Act: -0.0000

Data Index: 861700 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0513. Min Act: -0.0000

Data Index: 185711 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0445. Min Act: -0.0000

Data Index: 635885 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0461. Min Act: -0.0000

Data Index: 730265 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0434. Min Act: -0.0000

Data Index: 944845 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0433. Min Act: -0.0000

Data Index: 686210 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0408. Min Act: -0.0000

Data Index: 806215 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0411. Min Act: -0.0000

Data Index: 1218073 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0386. Min Act: -0.0000

Data Index: 1211688 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0413. Min Act: -0.0000

Data Index: 727501 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0407. Min Act: -0.0000

Data Index: 206875 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0389. Min Act: -0.0000

Data Index: 1044709 (C4 (Web Text))

Max Activating Token Index: 47