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

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

Neuron 24 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1402442 (Python Code)

Max Activating Token Index: 956

Text #1

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0622. Min Act: -0.0001

Data Index: 748125 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1508543 (Python Code)

Max Activating Token Index: 45

Text #3

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0629. Min Act: -0.0001

Data Index: 748564 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1475890 (Python Code)

Max Activating Token Index: 744

Text #5

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0534. Min Act: -0.0001

Data Index: 551730 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0544. Min Act: -0.0001

Data Index: 384399 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1366642 (Python Code)

Max Activating Token Index: 497

Text #8

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0503. Min Act: -0.0002

Data Index: 17702 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1396167 (Python Code)

Max Activating Token Index: 888

Text #10

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0517. Min Act: -0.0001

Data Index: 395289 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0481. Min Act: -0.0001

Data Index: 83955 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1446567 (Python Code)

Max Activating Token Index: 906

Text #13

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1373730 (Python Code)

Max Activating Token Index: 791

Text #14

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1102828 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1466944 (Python Code)

Max Activating Token Index: 767

Text #16

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1605016 (Python Code)

Max Activating Token Index: 195

Text #17

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0510. Min Act: -0.0002

Data Index: 502781 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1146165 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1567026 (Python Code)

Max Activating Token Index: 519