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

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

Neuron 4377 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3131. Min Range: -1.3131

Max Act: 1.3131. Min Act: -0.0000

Data Index: 686882 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 1.3131. Min Range: -1.3131

Max Act: 1.2210. Min Act: -0.0000

Data Index: 873254 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 1.3131. Min Range: -1.3131

Max Act: 1.0481. Min Act: -0.0000

Data Index: 308159 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 1.3131. Min Range: -1.3131

Max Act: 1.0383. Min Act: -0.0000

Data Index: 454729 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1307549 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 1.3131. Min Range: -1.3131

Max Act: 1.0135. Min Act: -0.0000

Data Index: 1281565 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9155. Min Act: -0.0000

Data Index: 1246675 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9216. Min Act: -0.0000

Data Index: 726767 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9045. Min Act: -0.0000

Data Index: 666855 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.8801. Min Act: -0.0000

Data Index: 878640 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1048906 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9284. Min Act: -0.0000

Data Index: 702815 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9535. Min Act: -0.0000

Data Index: 625863 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.8830. Min Act: -0.0000

Data Index: 418314 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.8622. Min Act: -0.0000

Data Index: 366743 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.8162. Min Act: -0.0000

Data Index: 934077 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.8471. Min Act: 0.0000

Data Index: 554189 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.8676. Min Act: -0.0000

Data Index: 317232 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.8116. Min Act: -0.0000

Data Index: 649570 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1300428 (C4 (Web Text))

Max Activating Token Index: 286