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

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

Neuron 2010 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.7841. Min Act: -0.0000

Data Index: 986438 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1114686 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1244264 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6662. Min Act: -0.0000

Data Index: 543895 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.7041. Min Act: -0.0000

Data Index: 289228 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6700. Min Act: -0.0000

Data Index: 122446 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6624. Min Act: -0.0000

Data Index: 298897 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6623. Min Act: -0.0000

Data Index: 974686 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6533. Min Act: -0.0000

Data Index: 443086 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6605. Min Act: -0.0000

Data Index: 470764 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6255. Min Act: -0.0000

Data Index: 412474 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6504. Min Act: -0.0000

Data Index: 856144 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6314. Min Act: -0.0000

Data Index: 69205 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6585. Min Act: -0.0000

Data Index: 996423 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6208. Min Act: -0.0000

Data Index: 268835 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6182. Min Act: -0.0000

Data Index: 928069 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.5902. Min Act: -0.0000

Data Index: 501179 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6560. Min Act: 0.0000

Data Index: 364476 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6239. Min Act: -0.0000

Data Index: 944031 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.7841. Min Range: -0.7841

Max Act: 0.6007. Min Act: -0.0000

Data Index: 942823 (C4 (Web Text))

Max Activating Token Index: 133