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

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

Neuron 5693 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: 0.9250. Min Range: -0.9250

Max Act: 0.9250. Min Act: -0.0000

Data Index: 1534295 (Python Code)

Max Activating Token Index: 435

Text #1

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.8972. Min Act: -0.0000

Data Index: 1613203 (Python Code)

Max Activating Token Index: 105

Text #2

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.8456. Min Act: -0.0000

Data Index: 1629070 (Python Code)

Max Activating Token Index: 753

Text #3

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1606446 (Python Code)

Max Activating Token Index: 839

Text #4

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1470419 (Python Code)

Max Activating Token Index: 197

Text #5

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1067322 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1610140 (Python Code)

Max Activating Token Index: 562

Text #7

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1633471 (Python Code)

Max Activating Token Index: 482

Text #8

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1393181 (Python Code)

Max Activating Token Index: 283

Text #9

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7557. Min Act: -0.0000

Data Index: 1592348 (Python Code)

Max Activating Token Index: 402

Text #10

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1474104 (Python Code)

Max Activating Token Index: 241

Text #11

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7816. Min Act: -0.0000

Data Index: 1434808 (Python Code)

Max Activating Token Index: 326

Text #12

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6844. Min Act: -0.0000

Data Index: 730567 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1202548 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1420097 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6979. Min Act: -0.0000

Data Index: 1164995 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1564518 (Python Code)

Max Activating Token Index: 768

Text #17

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6901. Min Act: -0.0000

Data Index: 978636 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7501. Min Act: -0.0000

Data Index: 234568 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1486112 (Python Code)

Max Activating Token Index: 440