Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 346 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1315. Min Range: -1.1315

Max Act: 1.1315. Min Act: -0.0001

Data Index: 1515835 (Python Code)

Max Activating Token Index: 200

Text #1

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.9513. Min Act: -0.0000

Data Index: 1507075 (Python Code)

Max Activating Token Index: 896

Text #2

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.9338. Min Act: -0.0000

Data Index: 1619301 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1540313 (Python Code)

Max Activating Token Index: 469

Text #4

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1621527 (Python Code)

Max Activating Token Index: 295

Text #5

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8978. Min Act: -0.0001

Data Index: 1474014 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8615. Min Act: -0.0001

Data Index: 1384492 (Python Code)

Max Activating Token Index: 62

Text #7

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1404140 (Python Code)

Max Activating Token Index: 170

Text #8

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1512595 (Python Code)

Max Activating Token Index: 828

Text #9

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8307. Min Act: -0.0001

Data Index: 1610270 (Python Code)

Max Activating Token Index: 431

Text #10

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1579497 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8752. Min Act: -0.0001

Data Index: 1361856 (Python Code)

Max Activating Token Index: 144

Text #12

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8273. Min Act: -0.0001

Data Index: 1457908 (Python Code)

Max Activating Token Index: 222

Text #13

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1413331 (Python Code)

Max Activating Token Index: 242

Text #14

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8406. Min Act: -0.0001

Data Index: 1625737 (Python Code)

Max Activating Token Index: 744

Text #15

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1628223 (Python Code)

Max Activating Token Index: 181

Text #16

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1497032 (Python Code)

Max Activating Token Index: 83

Text #17

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1623826 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.7875. Min Act: -0.0001

Data Index: 1605899 (Python Code)

Max Activating Token Index: 792

Text #19

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1561989 (Python Code)

Max Activating Token Index: 355