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

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

Neuron 3 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1298276 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.5137. Min Act: -0.0000

Data Index: 484956 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.5161. Min Act: -0.0000

Data Index: 482493 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1216865 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.4412. Min Act: -0.0000

Data Index: 17851 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.4664. Min Act: 0.0000

Data Index: 59925 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.4565. Min Act: -0.0000

Data Index: 12232 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1025606 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1185242 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.4502. Min Act: -0.0000

Data Index: 770793 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.4278. Min Act: -0.0000

Data Index: 870216 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1130414 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.4243. Min Act: -0.0000

Data Index: 737427 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.4150. Min Act: -0.0000

Data Index: 71952 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.4043. Min Act: -0.0000

Data Index: 542900 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1304381 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.4043. Min Act: 0.0000

Data Index: 463827 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.3959. Min Act: -0.0000

Data Index: 691960 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.3929. Min Act: -0.0000

Data Index: 273194 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.5665. Min Range: -0.5665

Max Act: 0.4061. Min Act: -0.0000

Data Index: 9912 (C4 (Web Text))

Max Activating Token Index: 841