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

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

Neuron 445 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: 2.1312. Min Range: -2.1312

Max Act: 2.1312. Min Act: -0.0000

Data Index: 1481286 (Python Code)

Max Activating Token Index: 624

Text #1

Max Range: 2.1312. Min Range: -2.1312

Max Act: 2.0360. Min Act: -0.0000

Data Index: 1439416 (Python Code)

Max Activating Token Index: 297

Text #2

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.9865. Min Act: -0.0000

Data Index: 1360296 (Python Code)

Max Activating Token Index: 965

Text #3

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.9644. Min Act: -0.0000

Data Index: 1499441 (Python Code)

Max Activating Token Index: 380

Text #4

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.9335. Min Act: -0.0000

Data Index: 1443812 (Python Code)

Max Activating Token Index: 438

Text #5

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7921. Min Act: -0.0000

Data Index: 1489606 (Python Code)

Max Activating Token Index: 894

Text #6

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7915. Min Act: -0.0000

Data Index: 1586735 (Python Code)

Max Activating Token Index: 379

Text #7

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7869. Min Act: -0.0000

Data Index: 1625616 (Python Code)

Max Activating Token Index: 133

Text #8

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7524. Min Act: -0.0000

Data Index: 1440885 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7407. Min Act: -0.0000

Data Index: 1394019 (Python Code)

Max Activating Token Index: 398

Text #10

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7238. Min Act: -0.0000

Data Index: 1080520 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6194. Min Act: -0.0000

Data Index: 1462864 (Python Code)

Max Activating Token Index: 250

Text #12

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.5859. Min Act: -0.0000

Data Index: 1609443 (Python Code)

Max Activating Token Index: 338

Text #13

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7436. Min Act: -0.0000

Data Index: 1367030 (Python Code)

Max Activating Token Index: 531

Text #14

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.5465. Min Act: -0.0000

Data Index: 1417753 (Python Code)

Max Activating Token Index: 698

Text #15

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6384. Min Act: -0.0000

Data Index: 1419422 (Python Code)

Max Activating Token Index: 964

Text #16

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6342. Min Act: -0.0000

Data Index: 1592486 (Python Code)

Max Activating Token Index: 292

Text #17

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7172. Min Act: -0.0000

Data Index: 1420003 (Python Code)

Max Activating Token Index: 62

Text #18

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6191. Min Act: -0.0000

Data Index: 1628903 (Python Code)

Max Activating Token Index: 119

Text #19

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6166. Min Act: -0.0000

Data Index: 1473808 (Python Code)

Max Activating Token Index: 532