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

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

Neuron 5035 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0117. Min Act: -0.0002

Data Index: 164134 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1535761 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1463692 (Python Code)

Max Activating Token Index: 755

Text #3

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1528387 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0046. Min Act: -0.0002

Data Index: 174859 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0044. Min Act: -0.0002

Data Index: 398606 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1393924 (Python Code)

Max Activating Token Index: 633

Text #7

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1055445 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0039. Min Act: -0.0002

Data Index: 895702 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1635638 (Python Code)

Max Activating Token Index: 192

Text #10

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1177158 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0040. Min Act: -0.0002

Data Index: 447584 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0043. Min Act: -0.0002

Data Index: 501639 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0035. Min Act: -0.0002

Data Index: 634008 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1276502 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0045. Min Act: -0.0002

Data Index: 267914 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0037. Min Act: -0.0002

Data Index: 586679 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0031. Min Act: -0.0002

Data Index: 1337635 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1421495 (Python Code)

Max Activating Token Index: 500

Text #19

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0041. Min Act: -0.0002

Data Index: 1437636 (Python Code)

Max Activating Token Index: 648