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

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

Neuron 6125 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0640. Min Range: -1.0640

Max Act: 1.0640. Min Act: -0.0000

Data Index: 1559062 (Python Code)

Max Activating Token Index: 932

Text #1

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1520896 (Python Code)

Max Activating Token Index: 207

Text #2

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8662. Min Act: -0.0000

Data Index: 1224998 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8037. Min Act: -0.0000

Data Index: 47373 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1504712 (Python Code)

Max Activating Token Index: 200

Text #5

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.6778. Min Act: -0.0000

Data Index: 852259 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1572947 (Python Code)

Max Activating Token Index: 80

Text #7

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.6909. Min Act: -0.0000

Data Index: 1385677 (Python Code)

Max Activating Token Index: 573

Text #8

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1488476 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1432487 (Python Code)

Max Activating Token Index: 145

Text #10

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1587343 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1478217 (Python Code)

Max Activating Token Index: 803

Text #12

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1383887 (Python Code)

Max Activating Token Index: 423

Text #13

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1631496 (Python Code)

Max Activating Token Index: 972

Text #14

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1549844 (Python Code)

Max Activating Token Index: 273

Text #15

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.6272. Min Act: -0.0000

Data Index: 717431 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1605579 (Python Code)

Max Activating Token Index: 740

Text #17

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1630487 (Python Code)

Max Activating Token Index: 620

Text #18

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5643. Min Act: -0.0000

Data Index: 39664 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1537311 (Python Code)

Max Activating Token Index: 855