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

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

Neuron 1875 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4007. Min Range: -6.4007

Max Act: 6.4007. Min Act: -0.0000

Data Index: 1396083 (Python Code)

Max Activating Token Index: 62

Text #1

Max Range: 6.4007. Min Range: -6.4007

Max Act: 6.3221. Min Act: -0.0000

Data Index: 1590218 (Python Code)

Max Activating Token Index: 194

Text #2

Max Range: 6.4007. Min Range: -6.4007

Max Act: 6.2310. Min Act: -0.0000

Data Index: 1472817 (Python Code)

Max Activating Token Index: 214

Text #3

Max Range: 6.4007. Min Range: -6.4007

Max Act: 5.6843. Min Act: -0.0000

Data Index: 1452331 (Python Code)

Max Activating Token Index: 88

Text #4

Max Range: 6.4007. Min Range: -6.4007

Max Act: 5.5760. Min Act: -0.0000

Data Index: 1369111 (Python Code)

Max Activating Token Index: 541

Text #5

Max Range: 6.4007. Min Range: -6.4007

Max Act: 5.5494. Min Act: -0.0000

Data Index: 1495932 (Python Code)

Max Activating Token Index: 974

Text #6

Max Range: 6.4007. Min Range: -6.4007

Max Act: 4.9705. Min Act: -0.0000

Data Index: 1630386 (Python Code)

Max Activating Token Index: 447

Text #7

Max Range: 6.4007. Min Range: -6.4007

Max Act: 5.2349. Min Act: -0.0000

Data Index: 1361189 (Python Code)

Max Activating Token Index: 319

Text #8

Max Range: 6.4007. Min Range: -6.4007

Max Act: 4.9477. Min Act: -0.0000

Data Index: 1443253 (Python Code)

Max Activating Token Index: 380

Text #9

Max Range: 6.4007. Min Range: -6.4007

Max Act: 4.9260. Min Act: -0.0000

Data Index: 1610124 (Python Code)

Max Activating Token Index: 86

Text #10

Max Range: 6.4007. Min Range: -6.4007

Max Act: 4.5524. Min Act: -0.0000

Data Index: 1439926 (Python Code)

Max Activating Token Index: 246

Text #11

Max Range: 6.4007. Min Range: -6.4007

Max Act: 4.7198. Min Act: -0.0000

Data Index: 1466046 (Python Code)

Max Activating Token Index: 333

Text #12

Max Range: 6.4007. Min Range: -6.4007

Max Act: 4.6641. Min Act: -0.0000

Data Index: 1608329 (Python Code)

Max Activating Token Index: 462

Text #13

Max Range: 6.4007. Min Range: -6.4007

Max Act: 4.6175. Min Act: -0.0000

Data Index: 1411786 (Python Code)

Max Activating Token Index: 431

Text #14

Max Range: 6.4007. Min Range: -6.4007

Max Act: 4.8945. Min Act: -0.0000

Data Index: 1611064 (Python Code)

Max Activating Token Index: 480

Text #15

Max Range: 6.4007. Min Range: -6.4007

Max Act: 4.5313. Min Act: -0.0000

Data Index: 1540140 (Python Code)

Max Activating Token Index: 364

Text #16

Max Range: 6.4007. Min Range: -6.4007

Max Act: 4.4987. Min Act: -0.0000

Data Index: 1597232 (Python Code)

Max Activating Token Index: 649

Text #17

Max Range: 6.4007. Min Range: -6.4007

Max Act: 4.4419. Min Act: -0.0000

Data Index: 1432914 (Python Code)

Max Activating Token Index: 300

Text #18

Max Range: 6.4007. Min Range: -6.4007

Max Act: 4.6104. Min Act: -0.0000

Data Index: 1571390 (Python Code)

Max Activating Token Index: 120

Text #19

Max Range: 6.4007. Min Range: -6.4007

Max Act: 4.6160. Min Act: -0.0000

Data Index: 1637665 (Python Code)

Max Activating Token Index: 511