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

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

Neuron 3838 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.3845. Min Act: -0.0001

Data Index: 1327935 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.2621. Min Act: -0.0001

Data Index: 136883 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0954. Min Act: -0.0001

Data Index: 999169 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.1619. Min Act: -0.0001

Data Index: 1260718 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0549. Min Act: -0.0001

Data Index: 69514 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0930. Min Act: -0.0001

Data Index: 1198210 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.1204. Min Act: -0.0001

Data Index: 1081540 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0434. Min Act: -0.0001

Data Index: 654103 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0107. Min Act: -0.0001

Data Index: 67582 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0313. Min Act: -0.0001

Data Index: 1278430 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0419. Min Act: -0.0001

Data Index: 1061829 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0868. Min Act: -0.0001

Data Index: 63363 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9947. Min Act: -0.0001

Data Index: 52645 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9523. Min Act: -0.0001

Data Index: 281590 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0422. Min Act: -0.0001

Data Index: 1039728 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0714. Min Act: -0.0001

Data Index: 536996 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0185. Min Act: -0.0001

Data Index: 623570 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9947. Min Act: -0.0001

Data Index: 962634 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9535. Min Act: -0.0001

Data Index: 1359600 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9835. Min Act: -0.0001

Data Index: 975011 (C4 (Web Text))

Max Activating Token Index: 631