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

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

Neuron 3926 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1041. Min Range: -1.1041

Max Act: 1.1041. Min Act: -0.0001

Data Index: 1462644 (Python Code)

Max Activating Token Index: 301

Text #1

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.9476. Min Act: -0.0001

Data Index: 1649817 (Python Code)

Max Activating Token Index: 493

Text #2

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8434. Min Act: -0.0001

Data Index: 1419391 (Python Code)

Max Activating Token Index: 879

Text #3

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1609143 (Python Code)

Max Activating Token Index: 38

Text #4

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.7842. Min Act: -0.0001

Data Index: 1400243 (Python Code)

Max Activating Token Index: 878

Text #5

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.7846. Min Act: -0.0001

Data Index: 1430973 (Python Code)

Max Activating Token Index: 611

Text #6

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.7489. Min Act: -0.0001

Data Index: 1613254 (Python Code)

Max Activating Token Index: 239

Text #7

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8171. Min Act: -0.0001

Data Index: 1424210 (Python Code)

Max Activating Token Index: 925

Text #8

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8267. Min Act: -0.0001

Data Index: 1559614 (Python Code)

Max Activating Token Index: 583

Text #9

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.7792. Min Act: -0.0001

Data Index: 1521903 (Python Code)

Max Activating Token Index: 795

Text #10

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.7607. Min Act: -0.0001

Data Index: 1602333 (Python Code)

Max Activating Token Index: 148

Text #11

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.6940. Min Act: -0.0001

Data Index: 1578049 (Python Code)

Max Activating Token Index: 917

Text #12

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1545898 (Python Code)

Max Activating Token Index: 938

Text #13

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.7506. Min Act: -0.0001

Data Index: 1505231 (Python Code)

Max Activating Token Index: 116

Text #14

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.7077. Min Act: -0.0001

Data Index: 1465555 (Python Code)

Max Activating Token Index: 44

Text #15

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.6971. Min Act: -0.0001

Data Index: 1411671 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1513784 (Python Code)

Max Activating Token Index: 90

Text #17

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.7254. Min Act: -0.0001

Data Index: 1478001 (Python Code)

Max Activating Token Index: 688

Text #18

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1423587 (Python Code)

Max Activating Token Index: 877

Text #19

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1621107 (Python Code)

Max Activating Token Index: 647