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

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

Neuron 4086 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: 0.0131. Min Range: -0.0131

Max Act: 0.0131. Min Act: -0.0003

Data Index: 799703 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0108. Min Act: -0.0003

Data Index: 601891 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0101. Min Act: -0.0003

Data Index: 1273866 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1149331 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0093. Min Act: -0.0003

Data Index: 356351 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0092. Min Act: -0.0003

Data Index: 52123 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0092. Min Act: -0.0003

Data Index: 890207 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0087. Min Act: -0.0003

Data Index: 864115 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0086. Min Act: -0.0003

Data Index: 37730 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0084. Min Act: -0.0003

Data Index: 608616 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0083. Min Act: -0.0003

Data Index: 75537 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1012752 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0075. Min Act: -0.0003

Data Index: 473820 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1475728 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1310616 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1040321 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0077. Min Act: -0.0003

Data Index: 991776 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1246898 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1320852 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0075. Min Act: -0.0003

Data Index: 434400 (C4 (Web Text))

Max Activating Token Index: 509