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

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

Neuron 3333 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: 1.6419. Min Range: -1.6419

Max Act: 1.6419. Min Act: -0.0001

Data Index: 506167 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5175. Min Act: -0.0001

Data Index: 304998 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5304. Min Act: -0.0001

Data Index: 1034849 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4020. Min Act: -0.0001

Data Index: 702819 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4007. Min Act: -0.0001

Data Index: 80058 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4265. Min Act: -0.0001

Data Index: 1036470 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.3484. Min Act: -0.0001

Data Index: 251201 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.1236. Min Act: -0.0001

Data Index: 1200605 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.1930. Min Act: -0.0001

Data Index: 782706 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.3271. Min Act: -0.0001

Data Index: 192163 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.2407. Min Act: -0.0001

Data Index: 867206 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.3091. Min Act: -0.0001

Data Index: 314429 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.3318. Min Act: -0.0001

Data Index: 684472 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.2204. Min Act: -0.0001

Data Index: 860667 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.1700. Min Act: -0.0001

Data Index: 1018518 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.2766. Min Act: -0.0001

Data Index: 208970 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.2784. Min Act: -0.0001

Data Index: 269828 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.3029. Min Act: -0.0001

Data Index: 278226 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.2125. Min Act: -0.0001

Data Index: 632051 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.2914. Min Act: -0.0001

Data Index: 734483 (C4 (Web Text))

Max Activating Token Index: 188