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

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

Neuron 2908 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.7140. Min Act: -0.0003

Data Index: 448720 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.7104. Min Act: -0.0003

Data Index: 580684 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6904. Min Act: -0.0003

Data Index: 177746 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6509. Min Act: -0.0002

Data Index: 230755 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6428. Min Act: -0.0003

Data Index: 856900 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6110. Min Act: -0.0003

Data Index: 75113 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6283. Min Act: -0.0003

Data Index: 310854 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6278. Min Act: -0.0003

Data Index: 956099 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5812. Min Act: -0.0002

Data Index: 470824 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6012. Min Act: -0.0003

Data Index: 1059285 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6195. Min Act: -0.0003

Data Index: 159333 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5818. Min Act: -0.0003

Data Index: 753332 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5629. Min Act: -0.0003

Data Index: 788822 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5598. Min Act: -0.0002

Data Index: 231326 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5549. Min Act: -0.0003

Data Index: 351071 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5601. Min Act: -0.0003

Data Index: 650098 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5803. Min Act: -0.0003

Data Index: 656240 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5565. Min Act: -0.0003

Data Index: 455206 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5543. Min Act: -0.0003

Data Index: 646855 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5433. Min Act: -0.0003

Data Index: 1316533 (C4 (Web Text))

Max Activating Token Index: 545