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

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

Neuron 3414 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: 2.5594. Min Range: -2.5594

Max Act: 2.5594. Min Act: -0.0000

Data Index: 304392 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.5064. Min Act: -0.0000

Data Index: 983234 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.4890. Min Act: -0.0000

Data Index: 693642 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.3859. Min Act: -0.0001

Data Index: 498511 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.3674. Min Act: -0.0000

Data Index: 1152370 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.3187. Min Act: -0.0000

Data Index: 135097 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.2946. Min Act: -0.0000

Data Index: 104622 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.1553. Min Act: -0.0000

Data Index: 1059149 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.2085. Min Act: -0.0001

Data Index: 369909 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.2538. Min Act: -0.0000

Data Index: 219265 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.1711. Min Act: -0.0000

Data Index: 1165556 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.1506. Min Act: -0.0000

Data Index: 1259569 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.1568. Min Act: -0.0001

Data Index: 529643 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.1362. Min Act: -0.0000

Data Index: 372423 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.0757. Min Act: -0.0000

Data Index: 447922 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.1269. Min Act: -0.0000

Data Index: 234155 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.1446. Min Act: -0.0000

Data Index: 285776 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.1668. Min Act: -0.0001

Data Index: 1155285 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.1144. Min Act: -0.0001

Data Index: 210785 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 2.5594. Min Range: -2.5594

Max Act: 2.0861. Min Act: -0.0000

Data Index: 340504 (C4 (Web Text))

Max Activating Token Index: 847