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

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

Neuron 5920 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0443. Min Range: -7.0443

Max Act: 7.0443. Min Act: -0.0000

Data Index: 1507846 (Python Code)

Max Activating Token Index: 44

Text #1

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.9918. Min Act: -0.0000

Data Index: 1546521 (Python Code)

Max Activating Token Index: 944

Text #2

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.8549. Min Act: -0.0000

Data Index: 1574661 (Python Code)

Max Activating Token Index: 49

Text #3

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.7296. Min Act: -0.0000

Data Index: 1564974 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.4771. Min Act: -0.0000

Data Index: 1591350 (Python Code)

Max Activating Token Index: 862

Text #5

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.6561. Min Act: -0.0000

Data Index: 1391817 (Python Code)

Max Activating Token Index: 497

Text #6

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.6351. Min Act: -0.0000

Data Index: 1437999 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.6206. Min Act: -0.0000

Data Index: 1535252 (Python Code)

Max Activating Token Index: 92

Text #8

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.6068. Min Act: -0.0000

Data Index: 1640861 (Python Code)

Max Activating Token Index: 648

Text #9

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.6069. Min Act: -0.0000

Data Index: 1380559 (Python Code)

Max Activating Token Index: 64

Text #10

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.5435. Min Act: -0.0000

Data Index: 1551651 (Python Code)

Max Activating Token Index: 163

Text #11

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.5241. Min Act: -0.0000

Data Index: 1546596 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.7190. Min Act: -0.0000

Data Index: 1588598 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.5069. Min Act: -0.0000

Data Index: 1486900 (Python Code)

Max Activating Token Index: 244

Text #14

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.5143. Min Act: -0.0000

Data Index: 1522718 (Python Code)

Max Activating Token Index: 60

Text #15

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.2275. Min Act: -0.0000

Data Index: 1420215 (Python Code)

Max Activating Token Index: 712

Text #16

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.2018. Min Act: -0.0000

Data Index: 1364098 (Python Code)

Max Activating Token Index: 705

Text #17

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.4000. Min Act: -0.0000

Data Index: 1361502 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.3682. Min Act: -0.0000

Data Index: 1360276 (Python Code)

Max Activating Token Index: 74

Text #19

Max Range: 7.0443. Min Range: -7.0443

Max Act: 6.4151. Min Act: -0.0000

Data Index: 1367818 (Python Code)

Max Activating Token Index: 429