Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 509 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.9110. Min Act: -0.0001

Data Index: 74468 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8777. Min Act: -0.0001

Data Index: 359391 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8696. Min Act: -0.0001

Data Index: 1106446 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8083. Min Act: -0.0001

Data Index: 653527 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8539. Min Act: -0.0001

Data Index: 234208 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8197. Min Act: -0.0001

Data Index: 1156428 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8415. Min Act: -0.0001

Data Index: 847540 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8284. Min Act: -0.0001

Data Index: 1209375 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7887. Min Act: -0.0001

Data Index: 492631 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7835. Min Act: -0.0001

Data Index: 1051259 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8033. Min Act: -0.0001

Data Index: 671422 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7684. Min Act: -0.0001

Data Index: 1038956 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7481. Min Act: -0.0001

Data Index: 251863 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7436. Min Act: -0.0001

Data Index: 183360 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7584. Min Act: -0.0001

Data Index: 780587 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7369. Min Act: -0.0001

Data Index: 1151736 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7556. Min Act: -0.0001

Data Index: 378373 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7288. Min Act: -0.0001

Data Index: 1008019 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6903. Min Act: -0.0001

Data Index: 649847 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7153. Min Act: -0.0001

Data Index: 574846 (C4 (Web Text))

Max Activating Token Index: 800