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

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

Neuron 587 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: 1.9121. Min Range: -1.9121

Max Act: 1.7797. Min Act: -0.0000

Data Index: 1608968 (Python Code)

Max Activating Token Index: 356

Text #1

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.9121. Min Act: -0.0000

Data Index: 1526040 (Python Code)

Max Activating Token Index: 154

Text #2

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.4277. Min Act: -0.0000

Data Index: 1480071 (Python Code)

Max Activating Token Index: 251

Text #3

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.3908. Min Act: -0.0000

Data Index: 1449710 (Python Code)

Max Activating Token Index: 52

Text #4

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.4199. Min Act: -0.0000

Data Index: 1380372 (Python Code)

Max Activating Token Index: 332

Text #5

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.3961. Min Act: -0.0000

Data Index: 1416416 (Python Code)

Max Activating Token Index: 395

Text #6

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.3250. Min Act: -0.0000

Data Index: 1406709 (Python Code)

Max Activating Token Index: 543

Text #7

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.2638. Min Act: -0.0000

Data Index: 1301536 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1634686 (Python Code)

Max Activating Token Index: 585

Text #9

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.1713. Min Act: -0.0000

Data Index: 716796 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.1319. Min Act: -0.0000

Data Index: 1502016 (Python Code)

Max Activating Token Index: 87

Text #11

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.1754. Min Act: -0.0000

Data Index: 1361376 (Python Code)

Max Activating Token Index: 463

Text #12

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1644157 (Python Code)

Max Activating Token Index: 440

Text #13

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.1278. Min Act: -0.0000

Data Index: 1359507 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.1454. Min Act: -0.0000

Data Index: 1200392 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1501800 (Python Code)

Max Activating Token Index: 155

Text #16

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.1491. Min Act: -0.0000

Data Index: 1574196 (Python Code)

Max Activating Token Index: 336

Text #17

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.1497. Min Act: -0.0000

Data Index: 1313744 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.1550. Min Act: -0.0000

Data Index: 1568175 (Python Code)

Max Activating Token Index: 718

Text #19

Max Range: 1.9121. Min Range: -1.9121

Max Act: 1.0521. Min Act: -0.0000

Data Index: 266156 (C4 (Web Text))

Max Activating Token Index: 318