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

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

Neuron 2176 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.4067. Min Act: -0.0000

Data Index: 932871 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1046455 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1133011 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3345. Min Act: -0.0000

Data Index: 1070338 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1004359 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2856. Min Act: -0.0000

Data Index: 244623 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3211. Min Act: -0.0000

Data Index: 377645 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3166. Min Act: -0.0000

Data Index: 39679 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2948. Min Act: -0.0000

Data Index: 902066 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2890. Min Act: -0.0000

Data Index: 1262780 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2618. Min Act: -0.0000

Data Index: 944251 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2835. Min Act: -0.0000

Data Index: 365249 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1185377 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2843. Min Act: -0.0000

Data Index: 379818 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2848. Min Act: -0.0000

Data Index: 87088 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2750. Min Act: -0.0000

Data Index: 738187 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2753. Min Act: -0.0000

Data Index: 436846 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2654. Min Act: -0.0000

Data Index: 677230 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1258421 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2813. Min Act: -0.0000

Data Index: 432645 (C4 (Web Text))

Max Activating Token Index: 352