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

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

Neuron 3203 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: 0.0136. Min Range: -0.0136

Max Act: 0.0136. Min Act: -0.0003

Data Index: 899008 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0084. Min Act: -0.0003

Data Index: 595096 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1100920 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0066. Min Act: -0.0003

Data Index: 34980 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0069. Min Act: -0.0003

Data Index: 163644 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0068. Min Act: -0.0003

Data Index: 701201 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0063. Min Act: -0.0003

Data Index: 792688 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0059. Min Act: -0.0003

Data Index: 932730 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0061. Min Act: -0.0003

Data Index: 121722 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0046. Min Act: -0.0003

Data Index: 771818 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0059. Min Act: -0.0003

Data Index: 276594 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0053. Min Act: -0.0003

Data Index: 287366 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0062. Min Act: -0.0003

Data Index: 773844 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0053. Min Act: -0.0003

Data Index: 132670 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1212141 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0054. Min Act: -0.0003

Data Index: 996352 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0051. Min Act: -0.0003

Data Index: 878776 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0054. Min Act: -0.0003

Data Index: 905464 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1202042 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0045. Min Act: -0.0003

Data Index: 7542 (C4 (Web Text))

Max Activating Token Index: 805