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

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

Neuron 1531 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: 0.4787. Min Range: -0.4787

Max Act: 0.4353. Min Act: -0.0000

Data Index: 685656 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4787. Min Act: -0.0000

Data Index: 427824 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3449. Min Act: -0.0000

Data Index: 636595 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1266835 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3360. Min Act: -0.0000

Data Index: 805389 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3228. Min Act: -0.0000

Data Index: 854988 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3236. Min Act: -0.0000

Data Index: 766965 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3237. Min Act: -0.0000

Data Index: 232650 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3018. Min Act: -0.0000

Data Index: 776312 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3308. Min Act: -0.0000

Data Index: 531633 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3417. Min Act: -0.0000

Data Index: 999426 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.2920. Min Act: -0.0000

Data Index: 1174796 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.2942. Min Act: -0.0000

Data Index: 116877 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1295943 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1093564 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1210995 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.2898. Min Act: -0.0000

Data Index: 155447 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3087. Min Act: -0.0000

Data Index: 537495 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.2668. Min Act: -0.0000

Data Index: 250489 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.2732. Min Act: -0.0000

Data Index: 329183 (C4 (Web Text))

Max Activating Token Index: 605