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

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

Neuron 2202 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.8133. Min Act: -0.0001

Data Index: 585903 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7800. Min Act: -0.0001

Data Index: 1333296 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7258. Min Act: -0.0001

Data Index: 1304362 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6302. Min Act: -0.0001

Data Index: 399774 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6503. Min Act: -0.0001

Data Index: 913518 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6651. Min Act: -0.0001

Data Index: 1178507 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6450. Min Act: -0.0001

Data Index: 113822 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6395. Min Act: -0.0001

Data Index: 142551 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6324. Min Act: -0.0001

Data Index: 942637 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6377. Min Act: -0.0001

Data Index: 1176536 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5875. Min Act: -0.0001

Data Index: 561453 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6274. Min Act: -0.0001

Data Index: 1035478 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6001. Min Act: -0.0001

Data Index: 1254935 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5982. Min Act: -0.0001

Data Index: 214809 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6054. Min Act: -0.0001

Data Index: 491748 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5885. Min Act: -0.0001

Data Index: 333069 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5743. Min Act: -0.0001

Data Index: 166928 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5570. Min Act: -0.0001

Data Index: 324171 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5952. Min Act: -0.0001

Data Index: 1213622 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5541. Min Act: -0.0001

Data Index: 111879 (C4 (Web Text))

Max Activating Token Index: 130