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

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

Neuron 1349 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4932. Min Act: -0.0000

Data Index: 1443835 (Python Code)

Max Activating Token Index: 660

Text #1

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.2705. Min Act: -0.0000

Data Index: 1435559 (Python Code)

Max Activating Token Index: 106

Text #2

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.2449. Min Act: -0.0000

Data Index: 210384 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.2212. Min Act: -0.0000

Data Index: 1469265 (Python Code)

Max Activating Token Index: 108

Text #4

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0853. Min Act: -0.0000

Data Index: 1513754 (Python Code)

Max Activating Token Index: 91

Text #5

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0824. Min Act: -0.0000

Data Index: 624831 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0113. Min Act: -0.0000

Data Index: 382463 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0791. Min Act: -0.0000

Data Index: 208277 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0572. Min Act: -0.0000

Data Index: 547350 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0454. Min Act: -0.0000

Data Index: 1454788 (Python Code)

Max Activating Token Index: 562

Text #10

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0362. Min Act: -0.0000

Data Index: 371511 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0886. Min Act: -0.0000

Data Index: 1216600 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.4932. Min Range: -1.4932

Max Act: 0.9925. Min Act: -0.0000

Data Index: 1540004 (Python Code)

Max Activating Token Index: 75

Text #13

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0009. Min Act: -0.0000

Data Index: 185783 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.1656. Min Act: -0.0000

Data Index: 461821 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1401905 (Python Code)

Max Activating Token Index: 287

Text #16

Max Range: 1.4932. Min Range: -1.4932

Max Act: 0.9100. Min Act: -0.0000

Data Index: 839405 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 1.4932. Min Range: -1.4932

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1120665 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 1.4932. Min Range: -1.4932

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1587491 (Python Code)

Max Activating Token Index: 136

Text #19

Max Range: 1.4932. Min Range: -1.4932

Max Act: 0.9037. Min Act: -0.0000

Data Index: 82740 (C4 (Web Text))

Max Activating Token Index: 840