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

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

Neuron 984 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0464. Min Act: -0.0002

Data Index: 193062 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0512. Min Act: -0.0002

Data Index: 921443 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1255737 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0486. Min Act: -0.0002

Data Index: 991096 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0446. Min Act: -0.0002

Data Index: 771984 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0439. Min Act: -0.0002

Data Index: 683066 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0469. Min Act: -0.0002

Data Index: 154663 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0002

Data Index: 355546 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0396. Min Act: -0.0002

Data Index: 995292 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1099025 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1192500 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1057080 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0404. Min Act: -0.0002

Data Index: 142610 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0419. Min Act: -0.0002

Data Index: 31244 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1133931 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0422. Min Act: -0.0002

Data Index: 438237 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0409. Min Act: -0.0002

Data Index: 79637 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1286703 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0421. Min Act: -0.0002

Data Index: 405039 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0450. Min Act: -0.0002

Data Index: 463878 (C4 (Web Text))

Max Activating Token Index: 592