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

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

Neuron 3676 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1157. Min Act: -0.0001

Data Index: 726973 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1154. Min Act: -0.0002

Data Index: 305293 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1221800 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1354118 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1240374 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1092. Min Act: -0.0001

Data Index: 770646 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1083. Min Act: -0.0001

Data Index: 633272 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1075. Min Act: -0.0002

Data Index: 307497 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0983. Min Act: -0.0001

Data Index: 154851 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0921. Min Act: -0.0001

Data Index: 795388 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1222841 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0933. Min Act: -0.0002

Data Index: 996339 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0944. Min Act: -0.0002

Data Index: 792172 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0955. Min Act: -0.0002

Data Index: 418054 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1354552 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0881. Min Act: -0.0002

Data Index: 634610 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0884. Min Act: -0.0002

Data Index: 369198 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0895. Min Act: -0.0001

Data Index: 840323 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0893. Min Act: -0.0002

Data Index: 581084 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0953. Min Act: -0.0001

Data Index: 130048 (C4 (Web Text))

Max Activating Token Index: 620