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

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

Neuron 4764 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1210900 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1549246 (Python Code)

Max Activating Token Index: 469

Text #2

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0900. Min Act: -0.0000

Data Index: 695747 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1403216 (Python Code)

Max Activating Token Index: 667

Text #4

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0902. Min Act: -0.0001

Data Index: 11294 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0763. Min Act: -0.0000

Data Index: 642450 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1592808 (Python Code)

Max Activating Token Index: 654

Text #7

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0904. Min Act: -0.0001

Data Index: 579551 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0654. Min Act: -0.0000

Data Index: 24364 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0678. Min Act: -0.0000

Data Index: 1425278 (Python Code)

Max Activating Token Index: 764

Text #10

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0749. Min Act: -0.0000

Data Index: 1329540 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0694. Min Act: -0.0000

Data Index: 414629 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0655. Min Act: -0.0000

Data Index: 147069 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0649. Min Act: -0.0001

Data Index: 338568 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0730. Min Act: -0.0000

Data Index: 1458245 (Python Code)

Max Activating Token Index: 129

Text #15

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0719. Min Act: -0.0000

Data Index: 781651 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0649. Min Act: -0.0000

Data Index: 500759 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1011767 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0705. Min Act: -0.0000

Data Index: 775762 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0781. Min Act: -0.0000

Data Index: 804730 (C4 (Web Text))

Max Activating Token Index: 771