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

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

Neuron 302 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.8333. Min Act: -0.0000

Data Index: 1484396 (Python Code)

Max Activating Token Index: 143

Text #1

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.8966. Min Act: -0.0000

Data Index: 1637822 (Python Code)

Max Activating Token Index: 165

Text #2

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.7638. Min Act: -0.0000

Data Index: 546100 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.6695. Min Act: -0.0000

Data Index: 1618774 (Python Code)

Max Activating Token Index: 760

Text #4

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.6511. Min Act: -0.0000

Data Index: 1386876 (Python Code)

Max Activating Token Index: 91

Text #5

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.5335. Min Act: -0.0000

Data Index: 1371041 (Python Code)

Max Activating Token Index: 324

Text #6

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.6302. Min Act: -0.0000

Data Index: 1366124 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.6290. Min Act: -0.0000

Data Index: 384950 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.6767. Min Act: -0.0000

Data Index: 1182555 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.5665. Min Act: -0.0000

Data Index: 1459830 (Python Code)

Max Activating Token Index: 870

Text #10

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.5541. Min Act: -0.0000

Data Index: 161942 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.5398. Min Act: -0.0000

Data Index: 766860 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.4501. Min Act: -0.0000

Data Index: 32075 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.5292. Min Act: -0.0000

Data Index: 20424 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.6298. Min Act: -0.0000

Data Index: 1345522 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.4385. Min Act: -0.0000

Data Index: 718950 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.5186. Min Act: -0.0000

Data Index: 1467238 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.5154. Min Act: -0.0000

Data Index: 1486562 (Python Code)

Max Activating Token Index: 948

Text #18

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.4086. Min Act: -0.0000

Data Index: 1501148 (Python Code)

Max Activating Token Index: 5

Text #19

Max Range: 1.8966. Min Range: -1.8966

Max Act: 1.4031. Min Act: -0.0000

Data Index: 1161492 (C4 (Web Text))

Max Activating Token Index: 168