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

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

Neuron 3672 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9835. Min Act: -0.0000

Data Index: 303052 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.6202. Min Act: -0.0000

Data Index: 820538 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.6226. Min Act: -0.0000

Data Index: 788196 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5954. Min Act: -0.0000

Data Index: 559025 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1096576 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5889. Min Act: -0.0000

Data Index: 527821 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1478527 (Python Code)

Max Activating Token Index: 82

Text #7

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1540608 (Python Code)

Max Activating Token Index: 41

Text #8

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5450. Min Act: -0.0000

Data Index: 255706 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5381. Min Act: -0.0000

Data Index: 1339542 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1415391 (Python Code)

Max Activating Token Index: 638

Text #11

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1637541 (Python Code)

Max Activating Token Index: 549

Text #12

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.4958. Min Act: -0.0000

Data Index: 987945 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1514142 (Python Code)

Max Activating Token Index: 244

Text #14

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5544. Min Act: -0.0000

Data Index: 592264 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.4906. Min Act: -0.0000

Data Index: 68986 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1532867 (Python Code)

Max Activating Token Index: 650

Text #17

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1531751 (Python Code)

Max Activating Token Index: 524

Text #18

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.4972. Min Act: -0.0000

Data Index: 306854 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5120. Min Act: -0.0000

Data Index: 992068 (C4 (Web Text))

Max Activating Token Index: 70