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

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

Neuron 1261 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: 1.1211. Min Range: -1.1211

Max Act: 1.1211. Min Act: -0.0001

Data Index: 262393 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8829. Min Act: -0.0001

Data Index: 873980 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9116. Min Act: -0.0001

Data Index: 402324 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8702. Min Act: -0.0001

Data Index: 899450 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8231. Min Act: -0.0001

Data Index: 449754 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8742. Min Act: -0.0001

Data Index: 680486 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8305. Min Act: -0.0001

Data Index: 529838 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8036. Min Act: -0.0001

Data Index: 202167 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8523. Min Act: -0.0001

Data Index: 807883 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8210. Min Act: -0.0001

Data Index: 801933 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8036. Min Act: -0.0001

Data Index: 606529 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8094. Min Act: -0.0001

Data Index: 354257 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.7778. Min Act: -0.0001

Data Index: 298872 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.7998. Min Act: -0.0001

Data Index: 899558 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.7893. Min Act: -0.0001

Data Index: 499687 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8109. Min Act: -0.0001

Data Index: 796633 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.7825. Min Act: -0.0001

Data Index: 933511 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.7761. Min Act: -0.0001

Data Index: 1199093 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.6987. Min Act: -0.0001

Data Index: 942560 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.7985. Min Act: -0.0001

Data Index: 321700 (C4 (Web Text))

Max Activating Token Index: 336