Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3476 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1201023 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1375179 (Python Code)

Max Activating Token Index: 738

Text #2

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1414274 (Python Code)

Max Activating Token Index: 653

Text #3

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1378. Min Act: -0.0000

Data Index: 437385 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1034927 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1596897 (Python Code)

Max Activating Token Index: 721

Text #6

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1305. Min Act: -0.0000

Data Index: 1460139 (Python Code)

Max Activating Token Index: 319

Text #7

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1353. Min Act: -0.0000

Data Index: 102917 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1219. Min Act: -0.0000

Data Index: 712640 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1385828 (Python Code)

Max Activating Token Index: 157

Text #10

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1208. Min Act: -0.0000

Data Index: 549447 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1239. Min Act: -0.0000

Data Index: 541485 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1252. Min Act: -0.0000

Data Index: 430595 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1580464 (Python Code)

Max Activating Token Index: 614

Text #14

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1615957 (Python Code)

Max Activating Token Index: 466

Text #15

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1599042 (Python Code)

Max Activating Token Index: 208

Text #16

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1635036 (Python Code)

Max Activating Token Index: 860

Text #17

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1092. Min Act: -0.0000

Data Index: 310535 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1167. Min Act: -0.0000

Data Index: 1532389 (Python Code)

Max Activating Token Index: 365

Text #19

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1491913 (Python Code)

Max Activating Token Index: 130