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

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

Neuron 3056 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5384. Min Range: -4.5384

Max Act: 4.4658. Min Act: -0.0000

Data Index: 1553440 (Python Code)

Max Activating Token Index: 986

Text #1

Max Range: 4.5384. Min Range: -4.5384

Max Act: 4.2295. Min Act: -0.0000

Data Index: 1562992 (Python Code)

Max Activating Token Index: 417

Text #2

Max Range: 4.5384. Min Range: -4.5384

Max Act: 4.5384. Min Act: -0.0000

Data Index: 1640037 (Python Code)

Max Activating Token Index: 115

Text #3

Max Range: 4.5384. Min Range: -4.5384

Max Act: 4.2208. Min Act: -0.0000

Data Index: 1424246 (Python Code)

Max Activating Token Index: 777

Text #4

Max Range: 4.5384. Min Range: -4.5384

Max Act: 4.2326. Min Act: -0.0000

Data Index: 1363148 (Python Code)

Max Activating Token Index: 170

Text #5

Max Range: 4.5384. Min Range: -4.5384

Max Act: 4.2066. Min Act: -0.0000

Data Index: 1556150 (Python Code)

Max Activating Token Index: 666

Text #6

Max Range: 4.5384. Min Range: -4.5384

Max Act: 4.3356. Min Act: -0.0000

Data Index: 1624077 (Python Code)

Max Activating Token Index: 976

Text #7

Max Range: 4.5384. Min Range: -4.5384

Max Act: 4.2141. Min Act: -0.0000

Data Index: 1557998 (Python Code)

Max Activating Token Index: 148

Text #8

Max Range: 4.5384. Min Range: -4.5384

Max Act: 4.0001. Min Act: -0.0000

Data Index: 1575160 (Python Code)

Max Activating Token Index: 390

Text #9

Max Range: 4.5384. Min Range: -4.5384

Max Act: 4.2842. Min Act: -0.0000

Data Index: 1361557 (Python Code)

Max Activating Token Index: 719

Text #10

Max Range: 4.5384. Min Range: -4.5384

Max Act: 3.9528. Min Act: -0.0000

Data Index: 1504695 (Python Code)

Max Activating Token Index: 340

Text #11

Max Range: 4.5384. Min Range: -4.5384

Max Act: 4.1078. Min Act: -0.0000

Data Index: 1542524 (Python Code)

Max Activating Token Index: 501

Text #12

Max Range: 4.5384. Min Range: -4.5384

Max Act: 4.2174. Min Act: -0.0000

Data Index: 1652210 (Python Code)

Max Activating Token Index: 581

Text #13

Max Range: 4.5384. Min Range: -4.5384

Max Act: 4.0839. Min Act: -0.0000

Data Index: 1542565 (Python Code)

Max Activating Token Index: 323

Text #14

Max Range: 4.5384. Min Range: -4.5384

Max Act: 3.9170. Min Act: -0.0000

Data Index: 1481558 (Python Code)

Max Activating Token Index: 371

Text #15

Max Range: 4.5384. Min Range: -4.5384

Max Act: 3.8871. Min Act: -0.0000

Data Index: 1493782 (Python Code)

Max Activating Token Index: 153

Text #16

Max Range: 4.5384. Min Range: -4.5384

Max Act: 3.6848. Min Act: -0.0000

Data Index: 1481786 (Python Code)

Max Activating Token Index: 529

Text #17

Max Range: 4.5384. Min Range: -4.5384

Max Act: 3.8039. Min Act: -0.0000

Data Index: 1419039 (Python Code)

Max Activating Token Index: 639

Text #18

Max Range: 4.5384. Min Range: -4.5384

Max Act: 3.9498. Min Act: -0.0000

Data Index: 1599372 (Python Code)

Max Activating Token Index: 543

Text #19

Max Range: 4.5384. Min Range: -4.5384

Max Act: 3.4691. Min Act: -0.0000

Data Index: 1480369 (Python Code)

Max Activating Token Index: 145