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

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

Neuron 534 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: 0.9841. Min Range: -0.9841

Max Act: 0.9841. Min Act: -0.0001

Data Index: 760317 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9832. Min Act: -0.0001

Data Index: 422933 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9656. Min Act: -0.0000

Data Index: 344930 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9236. Min Act: -0.0001

Data Index: 1132256 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8916. Min Act: -0.0001

Data Index: 988981 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9082. Min Act: -0.0001

Data Index: 527568 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9339. Min Act: -0.0001

Data Index: 1299711 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9188. Min Act: -0.0001

Data Index: 1283339 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8666. Min Act: -0.0000

Data Index: 137682 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8575. Min Act: -0.0001

Data Index: 106079 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8792. Min Act: -0.0001

Data Index: 893103 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8805. Min Act: -0.0001

Data Index: 129285 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9022. Min Act: -0.0001

Data Index: 466901 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8399. Min Act: -0.0001

Data Index: 541836 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9268. Min Act: -0.0001

Data Index: 603062 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8067. Min Act: -0.0001

Data Index: 117322 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8289. Min Act: -0.0001

Data Index: 438665 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9021. Min Act: -0.0001

Data Index: 104961 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8533. Min Act: -0.0001

Data Index: 252905 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8453. Min Act: -0.0001

Data Index: 858823 (C4 (Web Text))

Max Activating Token Index: 416