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

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

Neuron 3566 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: 1.0011. Min Range: -1.0011

Max Act: 0.9762. Min Act: -0.0001

Data Index: 260889 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.9518. Min Act: -0.0001

Data Index: 1618168 (Python Code)

Max Activating Token Index: 544

Text #2

Max Range: 1.0011. Min Range: -1.0011

Max Act: 1.0011. Min Act: -0.0001

Data Index: 459263 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 1.0011. Min Range: -1.0011

Max Act: 1.0003. Min Act: -0.0001

Data Index: 472040 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.9308. Min Act: -0.0000

Data Index: 118260 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.8097. Min Act: -0.0001

Data Index: 1425548 (Python Code)

Max Activating Token Index: 323

Text #6

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.8018. Min Act: -0.0001

Data Index: 1336707 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1397624 (Python Code)

Max Activating Token Index: 147

Text #8

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.7627. Min Act: -0.0001

Data Index: 1557636 (Python Code)

Max Activating Token Index: 812

Text #9

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.7629. Min Act: -0.0001

Data Index: 485805 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.7691. Min Act: -0.0000

Data Index: 808541 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.7626. Min Act: -0.0000

Data Index: 752605 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.7300. Min Act: -0.0000

Data Index: 52360 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.7015. Min Act: -0.0001

Data Index: 886494 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.7179. Min Act: -0.0001

Data Index: 1355278 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.6948. Min Act: -0.0001

Data Index: 765347 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.7187. Min Act: -0.0001

Data Index: 1450536 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1411452 (Python Code)

Max Activating Token Index: 159

Text #18

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.6898. Min Act: -0.0000

Data Index: 773572 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 1.0011. Min Range: -1.0011

Max Act: 0.6853. Min Act: -0.0001

Data Index: 1378580 (Python Code)

Max Activating Token Index: 631