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

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

Neuron 482 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1278. Min Act: -0.0000

Data Index: 330059 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0984. Min Act: -0.0001

Data Index: 903228 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0885. Min Act: -0.0000

Data Index: 850025 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0807. Min Act: -0.0000

Data Index: 501331 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0761. Min Act: -0.0001

Data Index: 745331 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0759. Min Act: -0.0000

Data Index: 991489 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1331182 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1449070 (Python Code)

Max Activating Token Index: 849

Text #8

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0563. Min Act: -0.0000

Data Index: 851124 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1553677 (Python Code)

Max Activating Token Index: 384

Text #10

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1369118 (Python Code)

Max Activating Token Index: 965

Text #11

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1527206 (Python Code)

Max Activating Token Index: 558

Text #12

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0542. Min Act: -0.0000

Data Index: 397709 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1361181 (Python Code)

Max Activating Token Index: 398

Text #14

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0512. Min Act: -0.0001

Data Index: 98665 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1528493 (Python Code)

Max Activating Token Index: 607

Text #16

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1438265 (Python Code)

Max Activating Token Index: 534

Text #17

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0479. Min Act: -0.0001

Data Index: 1368654 (Python Code)

Max Activating Token Index: 851

Text #18

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0466. Min Act: -0.0001

Data Index: 1480610 (Python Code)

Max Activating Token Index: 231

Text #19

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1446994 (Python Code)

Max Activating Token Index: 555