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

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

Neuron 536 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0154. Min Act: -0.0002

Data Index: 988105 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0150. Min Act: -0.0002

Data Index: 749081 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0138. Min Act: -0.0002

Data Index: 115492 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0111. Min Act: -0.0002

Data Index: 908473 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0106. Min Act: -0.0002

Data Index: 749646 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0105. Min Act: -0.0002

Data Index: 930068 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0104. Min Act: -0.0002

Data Index: 402659 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1316511 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0089. Min Act: -0.0002

Data Index: 153500 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0091. Min Act: -0.0002

Data Index: 710616 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0084. Min Act: -0.0002

Data Index: 556620 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1154719 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1133355 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0086. Min Act: -0.0002

Data Index: 594067 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0081. Min Act: -0.0002

Data Index: 879168 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0081. Min Act: -0.0002

Data Index: 930788 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0077. Min Act: -0.0002

Data Index: 117306 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0077. Min Act: -0.0002

Data Index: 612677 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0077. Min Act: -0.0002

Data Index: 467862 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0076. Min Act: -0.0002

Data Index: 835424 (C4 (Web Text))

Max Activating Token Index: 335