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

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

Neuron 906 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: 4.0961. Min Range: -4.0961

Max Act: 4.0961. Min Act: -0.0000

Data Index: 1148769 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.7853. Min Act: -0.0000

Data Index: 571800 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.7375. Min Act: -0.0000

Data Index: 176636 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.5431. Min Act: -0.0000

Data Index: 904063 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.0127. Min Act: -0.0000

Data Index: 847651 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.2733. Min Act: -0.0000

Data Index: 1359079 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.0353. Min Act: -0.0000

Data Index: 73878 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.3391. Min Act: -0.0000

Data Index: 414615 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.1680. Min Act: -0.0000

Data Index: 817847 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.0166. Min Act: -0.0000

Data Index: 1263906 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 4.0961. Min Range: -4.0961

Max Act: 2.9933. Min Act: -0.0000

Data Index: 889754 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 4.0961. Min Range: -4.0961

Max Act: 2.7085. Min Act: -0.0000

Data Index: 1168153 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.0863. Min Act: -0.0000

Data Index: 201923 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 4.0961. Min Range: -4.0961

Max Act: 2.9160. Min Act: -0.0000

Data Index: 1076071 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 4.0961. Min Range: -4.0961

Max Act: 2.8447. Min Act: -0.0000

Data Index: 822806 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 4.0961. Min Range: -4.0961

Max Act: 2.8061. Min Act: -0.0000

Data Index: 686790 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.0756. Min Act: -0.0000

Data Index: 349895 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 4.0961. Min Range: -4.0961

Max Act: 2.7597. Min Act: -0.0000

Data Index: 890145 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 4.0961. Min Range: -4.0961

Max Act: 2.7641. Min Act: -0.0000

Data Index: 772983 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 4.0961. Min Range: -4.0961

Max Act: 2.6875. Min Act: -0.0000

Data Index: 607640 (C4 (Web Text))

Max Activating Token Index: 185