Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 392 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1981. Min Range: -1.1981

Max Act: 1.1981. Min Act: -0.0001

Data Index: 962298 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 1.1981. Min Range: -1.1981

Max Act: 1.1430. Min Act: -0.0001

Data Index: 1386918 (Python Code)

Max Activating Token Index: 716

Text #2

Max Range: 1.1981. Min Range: -1.1981

Max Act: 1.0673. Min Act: -0.0001

Data Index: 1540888 (Python Code)

Max Activating Token Index: 781

Text #3

Max Range: 1.1981. Min Range: -1.1981

Max Act: 1.0528. Min Act: -0.0001

Data Index: 638944 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.9966. Min Act: -0.0001

Data Index: 148799 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 1.1981. Min Range: -1.1981

Max Act: 1.0081. Min Act: -0.0000

Data Index: 637714 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.9788. Min Act: -0.0001

Data Index: 835428 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.9590. Min Act: -0.0001

Data Index: 212964 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1256882 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.9333. Min Act: -0.0001

Data Index: 1543342 (Python Code)

Max Activating Token Index: 137

Text #10

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.9384. Min Act: -0.0001

Data Index: 568182 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.8963. Min Act: -0.0001

Data Index: 1427509 (Python Code)

Max Activating Token Index: 787

Text #12

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.8611. Min Act: -0.0001

Data Index: 310347 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.8791. Min Act: -0.0001

Data Index: 1539771 (Python Code)

Max Activating Token Index: 297

Text #14

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.8985. Min Act: -0.0001

Data Index: 998705 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.7692. Min Act: -0.0001

Data Index: 1395322 (Python Code)

Max Activating Token Index: 580

Text #16

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.8776. Min Act: -0.0000

Data Index: 451021 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.8751. Min Act: -0.0001

Data Index: 413323 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.8486. Min Act: -0.0001

Data Index: 752328 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 1.1981. Min Range: -1.1981

Max Act: 0.8481. Min Act: -0.0001

Data Index: 1540750 (Python Code)

Max Activating Token Index: 571