Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 928 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.6102. Min Act: -0.0002

Data Index: 658071 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.6107. Min Act: -0.0002

Data Index: 1034316 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.6108. Min Act: -0.0002

Data Index: 1105519 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.6004. Min Act: -0.0002

Data Index: 733283 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.6083. Min Act: -0.0002

Data Index: 64668 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.6010. Min Act: -0.0003

Data Index: 862230 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5913. Min Act: -0.0003

Data Index: 642294 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5972. Min Act: -0.0002

Data Index: 306483 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5892. Min Act: -0.0002

Data Index: 635072 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5898. Min Act: -0.0002

Data Index: 525580 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5789. Min Act: -0.0002

Data Index: 1317119 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5701. Min Act: -0.0002

Data Index: 1243551 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5748. Min Act: -0.0002

Data Index: 1183841 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5874. Min Act: -0.0002

Data Index: 566268 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5777. Min Act: -0.0002

Data Index: 562666 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5733. Min Act: -0.0002

Data Index: 214941 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5645. Min Act: -0.0002

Data Index: 1306829 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5703. Min Act: -0.0002

Data Index: 1263186 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5588. Min Act: -0.0002

Data Index: 1087243 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5622. Min Act: -0.0002

Data Index: 1174106 (C4 (Web Text))

Max Activating Token Index: 646