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

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

Neuron 2774 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0946. Min Act: -0.0001

Data Index: 865904 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1627184 (Python Code)

Max Activating Token Index: 85

Text #2

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0531. Min Act: -0.0001

Data Index: 382526 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1308829 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0475. Min Act: -0.0001

Data Index: 234828 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0462. Min Act: -0.0001

Data Index: 195992 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0455. Min Act: -0.0002

Data Index: 381689 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1095106 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0439. Min Act: -0.0001

Data Index: 85654 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0436. Min Act: -0.0002

Data Index: 885217 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0434. Min Act: -0.0002

Data Index: 168932 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0425. Min Act: -0.0001

Data Index: 957937 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0410. Min Act: -0.0001

Data Index: 917771 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1197988 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1148662 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0401. Min Act: -0.0001

Data Index: 695112 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0400. Min Act: -0.0001

Data Index: 1055712 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0398. Min Act: -0.0001

Data Index: 827658 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0396. Min Act: -0.0001

Data Index: 939555 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0388. Min Act: -0.0002

Data Index: 434218 (C4 (Web Text))

Max Activating Token Index: 160