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

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

Neuron 4137 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: 1.0508. Min Range: -1.0508

Max Act: 1.0366. Min Act: -0.0000

Data Index: 447021 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 1.0508. Min Range: -1.0508

Max Act: 1.0508. Min Act: -0.0000

Data Index: 1001948 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.0508. Min Range: -1.0508

Max Act: 1.0264. Min Act: -0.0000

Data Index: 236455 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.9489. Min Act: -0.0000

Data Index: 1294562 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.9973. Min Act: -0.0000

Data Index: 880594 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.9665. Min Act: -0.0000

Data Index: 408633 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.9661. Min Act: -0.0000

Data Index: 665954 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.9062. Min Act: -0.0000

Data Index: 51625 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.9495. Min Act: -0.0000

Data Index: 682717 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.9259. Min Act: -0.0000

Data Index: 1417773 (Python Code)

Max Activating Token Index: 743

Text #10

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.8859. Min Act: -0.0000

Data Index: 469355 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1200846 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.8728. Min Act: -0.0000

Data Index: 755458 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1040552 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1139731 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.8696. Min Act: -0.0000

Data Index: 789145 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.8822. Min Act: -0.0000

Data Index: 495672 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.8949. Min Act: -0.0000

Data Index: 428881 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.8483. Min Act: -0.0000

Data Index: 731119 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 1.0508. Min Range: -1.0508

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1085975 (C4 (Web Text))

Max Activating Token Index: 457