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

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

Neuron 2642 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1355132 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1141732 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0069. Min Act: -0.0003

Data Index: 896378 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 465530 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1157676 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1226457 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0004

Data Index: 1090223 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 408075 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1105729 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1596519 (Python Code)

Max Activating Token Index: 569

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0003

Data Index: 837954 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1638888 (Python Code)

Max Activating Token Index: 404

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1029670 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0053. Min Act: -0.0003

Data Index: 695904 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0052. Min Act: -0.0003

Data Index: 823460 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0054. Min Act: -0.0003

Data Index: 5491 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1062199 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0053. Min Act: -0.0003

Data Index: 5096 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1297356 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1098650 (C4 (Web Text))

Max Activating Token Index: 420