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

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

Neuron 954 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: 1.0332. Min Range: -1.0332

Max Act: 1.0332. Min Act: -0.0000

Data Index: 205734 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1129015 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.7162. Min Act: -0.0000

Data Index: 150636 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1045182 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.6962. Min Act: -0.0000

Data Index: 527463 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1119178 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.6504. Min Act: -0.0000

Data Index: 12500 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.5859. Min Act: -0.0000

Data Index: 901245 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.6027. Min Act: -0.0000

Data Index: 939099 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.5971. Min Act: -0.0000

Data Index: 724791 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.6118. Min Act: -0.0000

Data Index: 400040 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.5944. Min Act: -0.0000

Data Index: 967633 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.5747. Min Act: -0.0000

Data Index: 439275 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1276552 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.5790. Min Act: -0.0000

Data Index: 556533 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.5700. Min Act: -0.0000

Data Index: 277388 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1134624 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.5783. Min Act: -0.0000

Data Index: 328871 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.5394. Min Act: -0.0000

Data Index: 746455 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 1.0332. Min Range: -1.0332

Max Act: 0.5586. Min Act: -0.0000

Data Index: 434945 (C4 (Web Text))

Max Activating Token Index: 742