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

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

Neuron 221 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6992. Min Act: -0.0000

Data Index: 12161 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.7094. Min Act: 0.0000

Data Index: 1130228 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6819. Min Act: -0.0000

Data Index: 1147720 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6713. Min Act: -0.0000

Data Index: 996750 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6047. Min Act: -0.0000

Data Index: 685890 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5486. Min Act: -0.0000

Data Index: 452928 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5662. Min Act: -0.0000

Data Index: 812522 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1003731 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5837. Min Act: -0.0000

Data Index: 239959 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5450. Min Act: 0.0000

Data Index: 1151210 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5498. Min Act: -0.0000

Data Index: 564264 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5391. Min Act: -0.0000

Data Index: 669231 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5366. Min Act: -0.0000

Data Index: 894323 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1307377 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5142. Min Act: -0.0000

Data Index: 722154 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5152. Min Act: -0.0000

Data Index: 491368 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5244. Min Act: 0.0000

Data Index: 1075812 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5394. Min Act: -0.0000

Data Index: 645652 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.4897. Min Act: -0.0000

Data Index: 806079 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5189. Min Act: -0.0000

Data Index: 444550 (C4 (Web Text))

Max Activating Token Index: 398