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

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

Neuron 4890 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2130. Min Range: -4.2130

Max Act: 4.2130. Min Act: -0.0000

Data Index: 224715 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 4.2130. Min Range: -4.2130

Max Act: 3.7019. Min Act: -0.0000

Data Index: 662625 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 4.2130. Min Range: -4.2130

Max Act: 3.5757. Min Act: -0.0000

Data Index: 576338 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 4.2130. Min Range: -4.2130

Max Act: 3.5597. Min Act: -0.0000

Data Index: 1261751 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 4.2130. Min Range: -4.2130

Max Act: 3.5355. Min Act: -0.0000

Data Index: 302172 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 4.2130. Min Range: -4.2130

Max Act: 3.1883. Min Act: -0.0000

Data Index: 151368 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 4.2130. Min Range: -4.2130

Max Act: 3.0668. Min Act: -0.0000

Data Index: 561809 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 4.2130. Min Range: -4.2130

Max Act: 3.0148. Min Act: -0.0000

Data Index: 1262161 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 4.2130. Min Range: -4.2130

Max Act: 3.0067. Min Act: -0.0000

Data Index: 554242 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 4.2130. Min Range: -4.2130

Max Act: 3.0128. Min Act: -0.0000

Data Index: 969124 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 4.2130. Min Range: -4.2130

Max Act: 3.0004. Min Act: -0.0000

Data Index: 713084 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 4.2130. Min Range: -4.2130

Max Act: 2.8208. Min Act: -0.0000

Data Index: 1024098 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 4.2130. Min Range: -4.2130

Max Act: 3.1040. Min Act: -0.0000

Data Index: 622148 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 4.2130. Min Range: -4.2130

Max Act: 2.7736. Min Act: -0.0000

Data Index: 561431 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 4.2130. Min Range: -4.2130

Max Act: 2.7146. Min Act: -0.0000

Data Index: 738152 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 4.2130. Min Range: -4.2130

Max Act: 2.8205. Min Act: -0.0000

Data Index: 393046 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 4.2130. Min Range: -4.2130

Max Act: 2.7762. Min Act: -0.0000

Data Index: 930146 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 4.2130. Min Range: -4.2130

Max Act: 2.7747. Min Act: -0.0000

Data Index: 724154 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 4.2130. Min Range: -4.2130

Max Act: 2.7589. Min Act: -0.0000

Data Index: 404512 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 4.2130. Min Range: -4.2130

Max Act: 2.4666. Min Act: -0.0000

Data Index: 538193 (C4 (Web Text))

Max Activating Token Index: 939