Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3551 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.8056. Min Act: -0.0000

Data Index: 987890 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7146. Min Act: -0.0000

Data Index: 965736 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1230553 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1297938 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.6219. Min Act: -0.0000

Data Index: 575720 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.5983. Min Act: -0.0000

Data Index: 577465 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.6098. Min Act: -0.0000

Data Index: 954084 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.6097. Min Act: -0.0000

Data Index: 650487 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.6010. Min Act: -0.0000

Data Index: 111030 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1248039 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1276177 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.6049. Min Act: -0.0000

Data Index: 305415 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.5342. Min Act: -0.0000

Data Index: 954756 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.5416. Min Act: -0.0000

Data Index: 118807 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.5455. Min Act: -0.0000

Data Index: 66416 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.5444. Min Act: -0.0000

Data Index: 929353 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.5069. Min Act: -0.0000

Data Index: 798280 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.4949. Min Act: -0.0000

Data Index: 1022123 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.5330. Min Act: -0.0000

Data Index: 1324303 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.4993. Min Act: -0.0000

Data Index: 860800 (C4 (Web Text))

Max Activating Token Index: 354