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

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

Neuron 1667 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8445. Min Act: -0.0003

Data Index: 554640 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8302. Min Act: -0.0003

Data Index: 992834 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8235. Min Act: -0.0003

Data Index: 787245 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7462. Min Act: -0.0003

Data Index: 1108939 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8121. Min Act: -0.0003

Data Index: 781652 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7988. Min Act: -0.0003

Data Index: 1314517 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8185. Min Act: -0.0003

Data Index: 475231 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8084. Min Act: -0.0003

Data Index: 1259015 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7910. Min Act: -0.0003

Data Index: 1330538 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7607. Min Act: -0.0003

Data Index: 268041 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7538. Min Act: -0.0003

Data Index: 1244112 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7786. Min Act: -0.0003

Data Index: 922873 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6654. Min Act: -0.0003

Data Index: 1255381 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7770. Min Act: -0.0003

Data Index: 705246 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7725. Min Act: -0.0003

Data Index: 396856 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6017. Min Act: -0.0003

Data Index: 100513 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7150. Min Act: -0.0003

Data Index: 408944 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7351. Min Act: -0.0003

Data Index: 878814 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7359. Min Act: -0.0003

Data Index: 674677 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7335. Min Act: -0.0003

Data Index: 490281 (C4 (Web Text))

Max Activating Token Index: 358