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

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

Neuron 3593 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 377664 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 59021 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1224015 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0003

Data Index: 788884 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0003

Data Index: 445525 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0003

Data Index: 171183 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0003

Data Index: 808427 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0003

Data Index: 263891 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1195535 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0003

Data Index: 882236 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1116384 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0003

Data Index: 68613 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0003

Data Index: 151498 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0003

Data Index: 26393 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 638736 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 966969 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 847060 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 942596 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1110288 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1140700 (C4 (Web Text))

Max Activating Token Index: 516