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

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

Neuron 4810 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1640. Min Act: -0.0002

Data Index: 820248 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1634. Min Act: -0.0003

Data Index: 193597 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1663. Min Act: -0.0002

Data Index: 259202 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1536. Min Act: -0.0002

Data Index: 86676 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1241. Min Act: -0.0002

Data Index: 540727 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1168. Min Act: -0.0003

Data Index: 1172673 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1186. Min Act: -0.0003

Data Index: 1286928 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1137. Min Act: -0.0002

Data Index: 812591 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1170. Min Act: -0.0003

Data Index: 478187 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1141. Min Act: -0.0002

Data Index: 473057 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1055. Min Act: -0.0003

Data Index: 113770 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1047. Min Act: -0.0003

Data Index: 705943 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1069. Min Act: -0.0002

Data Index: 1063091 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1017. Min Act: -0.0002

Data Index: 305802 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1091. Min Act: -0.0002

Data Index: 698617 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1075. Min Act: -0.0002

Data Index: 1109440 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1083. Min Act: -0.0003

Data Index: 657839 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1040. Min Act: -0.0002

Data Index: 1171300 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1000. Min Act: -0.0003

Data Index: 428881 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.1663. Min Range: -0.1663

Max Act: 0.1026. Min Act: -0.0003

Data Index: 948191 (C4 (Web Text))

Max Activating Token Index: 68