Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4234 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.7595. Min Range: -4.7595

Max Act: 4.7595. Min Act: -0.0000

Data Index: 57380 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 4.7595. Min Range: -4.7595

Max Act: 4.7282. Min Act: -0.0000

Data Index: 953768 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 4.7595. Min Range: -4.7595

Max Act: 4.3553. Min Act: -0.0000

Data Index: 1358154 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 4.7595. Min Range: -4.7595

Max Act: 4.0842. Min Act: -0.0000

Data Index: 1243902 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 4.7595. Min Range: -4.7595

Max Act: 3.9318. Min Act: -0.0000

Data Index: 1117293 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 4.7595. Min Range: -4.7595

Max Act: 4.0483. Min Act: -0.0000

Data Index: 560716 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 4.7595. Min Range: -4.7595

Max Act: 3.5905. Min Act: -0.0000

Data Index: 463412 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 4.7595. Min Range: -4.7595

Max Act: 3.7369. Min Act: -0.0000

Data Index: 396286 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 4.7595. Min Range: -4.7595

Max Act: 3.6638. Min Act: -0.0000

Data Index: 7566 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 4.7595. Min Range: -4.7595

Max Act: 3.6283. Min Act: -0.0000

Data Index: 756739 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 4.7595. Min Range: -4.7595

Max Act: 3.2904. Min Act: -0.0000

Data Index: 1018111 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 4.7595. Min Range: -4.7595

Max Act: 3.2572. Min Act: -0.0000

Data Index: 722796 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 4.7595. Min Range: -4.7595

Max Act: 3.5402. Min Act: -0.0000

Data Index: 134438 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 4.7595. Min Range: -4.7595

Max Act: 3.2269. Min Act: -0.0000

Data Index: 532464 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 4.7595. Min Range: -4.7595

Max Act: 3.1822. Min Act: -0.0000

Data Index: 258787 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 4.7595. Min Range: -4.7595

Max Act: 2.9713. Min Act: -0.0000

Data Index: 805938 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 4.7595. Min Range: -4.7595

Max Act: 3.2272. Min Act: -0.0000

Data Index: 686524 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 4.7595. Min Range: -4.7595

Max Act: 3.3512. Min Act: -0.0000

Data Index: 763597 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 4.7595. Min Range: -4.7595

Max Act: 3.0699. Min Act: -0.0000

Data Index: 253302 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 4.7595. Min Range: -4.7595

Max Act: 3.0619. Min Act: -0.0000

Data Index: 881898 (C4 (Web Text))

Max Activating Token Index: 237