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

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

Neuron 4160 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2638. Min Range: -2.2638

Max Act: 2.2638. Min Act: -0.0000

Data Index: 641399 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 2.2638. Min Range: -2.2638

Max Act: 2.1464. Min Act: -0.0000

Data Index: 1210623 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 2.2638. Min Range: -2.2638

Max Act: 2.0748. Min Act: -0.0000

Data Index: 850683 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 2.2638. Min Range: -2.2638

Max Act: 2.1834. Min Act: -0.0000

Data Index: 60028 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.9218. Min Act: -0.0000

Data Index: 1246759 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.8739. Min Act: -0.0000

Data Index: 970132 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.8485. Min Act: -0.0000

Data Index: 1208346 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.8188. Min Act: -0.0000

Data Index: 322481 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.7477. Min Act: -0.0000

Data Index: 300739 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.8297. Min Act: -0.0000

Data Index: 909719 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.7072. Min Act: -0.0000

Data Index: 922016 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.6969. Min Act: -0.0000

Data Index: 1095385 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.6790. Min Act: -0.0000

Data Index: 1111302 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.7690. Min Act: -0.0000

Data Index: 498080 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.5863. Min Act: -0.0000

Data Index: 250891 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.6671. Min Act: -0.0000

Data Index: 1038502 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.7393. Min Act: -0.0000

Data Index: 249429 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.6401. Min Act: -0.0000

Data Index: 1297401 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.6215. Min Act: -0.0000

Data Index: 1214158 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 2.2638. Min Range: -2.2638

Max Act: 1.6253. Min Act: -0.0000

Data Index: 668826 (C4 (Web Text))

Max Activating Token Index: 265