Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5788 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.9163. Min Act: -0.0000

Data Index: 254936 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8275. Min Act: -0.0000

Data Index: 564368 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8548. Min Act: -0.0000

Data Index: 873955 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8047. Min Act: -0.0000

Data Index: 562875 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8418. Min Act: -0.0000

Data Index: 56558 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1112133 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7536. Min Act: -0.0000

Data Index: 115726 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7911. Min Act: -0.0000

Data Index: 923236 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8053. Min Act: -0.0000

Data Index: 326078 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7787. Min Act: -0.0000

Data Index: 521600 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7819. Min Act: -0.0000

Data Index: 309067 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7734. Min Act: -0.0000

Data Index: 234443 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7270. Min Act: -0.0000

Data Index: 213780 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1172922 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6903. Min Act: -0.0000

Data Index: 799235 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7355. Min Act: -0.0000

Data Index: 102846 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6690. Min Act: -0.0000

Data Index: 913029 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6788. Min Act: -0.0000

Data Index: 570240 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6684. Min Act: -0.0000

Data Index: 810355 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1019912 (C4 (Web Text))

Max Activating Token Index: 578