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

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

Neuron 1039 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: 1.1483. Min Range: -1.1483

Max Act: 1.1483. Min Act: -0.0001

Data Index: 131744 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 1.1483. Min Range: -1.1483

Max Act: 1.0795. Min Act: -0.0001

Data Index: 226765 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 1.1483. Min Range: -1.1483

Max Act: 1.0999. Min Act: -0.0001

Data Index: 1025972 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 1.1483. Min Range: -1.1483

Max Act: 1.0345. Min Act: -0.0001

Data Index: 1249935 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 1.1483. Min Range: -1.1483

Max Act: 1.0027. Min Act: -0.0000

Data Index: 734560 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.9694. Min Act: -0.0001

Data Index: 581156 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.9422. Min Act: -0.0001

Data Index: 295428 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.9405. Min Act: -0.0001

Data Index: 780505 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.9853. Min Act: -0.0001

Data Index: 540910 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.9840. Min Act: -0.0001

Data Index: 1248690 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.9263. Min Act: -0.0001

Data Index: 569531 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.9821. Min Act: -0.0001

Data Index: 12356 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.9438. Min Act: -0.0001

Data Index: 548055 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.9607. Min Act: -0.0000

Data Index: 218177 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.9216. Min Act: -0.0000

Data Index: 483722 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.9154. Min Act: -0.0001

Data Index: 370743 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.8972. Min Act: -0.0001

Data Index: 1151731 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.8964. Min Act: -0.0001

Data Index: 1068232 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.9186. Min Act: -0.0001

Data Index: 62162 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 1.1483. Min Range: -1.1483

Max Act: 0.8511. Min Act: -0.0001

Data Index: 1055036 (C4 (Web Text))

Max Activating Token Index: 126