Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1690 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.7369. Min Act: -0.0001

Data Index: 994135 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6850. Min Act: -0.0001

Data Index: 527694 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.7090. Min Act: -0.0001

Data Index: 291713 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6855. Min Act: -0.0001

Data Index: 953088 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.7407. Min Act: -0.0001

Data Index: 1351699 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6791. Min Act: -0.0001

Data Index: 5049 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.5846. Min Act: -0.0001

Data Index: 312247 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6101. Min Act: -0.0001

Data Index: 36632 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6265. Min Act: -0.0001

Data Index: 519287 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6163. Min Act: -0.0001

Data Index: 1040039 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6525. Min Act: -0.0001

Data Index: 497050 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6767. Min Act: -0.0001

Data Index: 630687 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6090. Min Act: -0.0001

Data Index: 1214638 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6420. Min Act: -0.0001

Data Index: 772588 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.5733. Min Act: -0.0001

Data Index: 1110078 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6070. Min Act: -0.0001

Data Index: 433038 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.5924. Min Act: -0.0001

Data Index: 170517 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.5703. Min Act: -0.0001

Data Index: 441471 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.5749. Min Act: -0.0001

Data Index: 1166166 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.5948. Min Act: -0.0001

Data Index: 662835 (C4 (Web Text))

Max Activating Token Index: 488