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

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

Neuron 4853 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: 1.8096. Min Range: -1.8096

Max Act: 1.8096. Min Act: -0.0002

Data Index: 552756 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.7731. Min Act: -0.0002

Data Index: 16334 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.7990. Min Act: -0.0002

Data Index: 573848 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.7304. Min Act: -0.0002

Data Index: 878935 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.7170. Min Act: -0.0002

Data Index: 91001 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.7008. Min Act: -0.0002

Data Index: 683124 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.6933. Min Act: -0.0002

Data Index: 42165 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.6736. Min Act: -0.0002

Data Index: 64505 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.6529. Min Act: -0.0002

Data Index: 1269067 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.6406. Min Act: -0.0002

Data Index: 244177 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.6539. Min Act: -0.0002

Data Index: 68123 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.6397. Min Act: -0.0002

Data Index: 907278 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.6116. Min Act: -0.0002

Data Index: 1194909 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.6295. Min Act: -0.0002

Data Index: 199398 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.5525. Min Act: -0.0002

Data Index: 914644 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.5791. Min Act: -0.0003

Data Index: 21364 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.5388. Min Act: -0.0002

Data Index: 936778 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.5786. Min Act: -0.0002

Data Index: 1040069 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.5717. Min Act: -0.0002

Data Index: 578183 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.8096. Min Range: -1.8096

Max Act: 1.5559. Min Act: -0.0002

Data Index: 1119654 (C4 (Web Text))

Max Activating Token Index: 996