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

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

Neuron 1639 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: 3.0086. Min Range: -3.0086

Max Act: 3.0086. Min Act: -0.0002

Data Index: 712188 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.9836. Min Act: -0.0002

Data Index: 965780 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.9419. Min Act: -0.0002

Data Index: 337707 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.7984. Min Act: -0.0002

Data Index: 37590 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.8067. Min Act: -0.0002

Data Index: 112123 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.7811. Min Act: -0.0002

Data Index: 244687 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.7208. Min Act: -0.0002

Data Index: 798519 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.7284. Min Act: -0.0002

Data Index: 108849 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.7468. Min Act: -0.0002

Data Index: 809424 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.6600. Min Act: -0.0002

Data Index: 741489 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.6586. Min Act: -0.0002

Data Index: 1312907 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.6633. Min Act: -0.0002

Data Index: 1237666 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.6453. Min Act: -0.0002

Data Index: 1104845 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.5429. Min Act: -0.0003

Data Index: 853 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.5780. Min Act: -0.0002

Data Index: 807869 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.5923. Min Act: -0.0002

Data Index: 529874 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.5703. Min Act: -0.0002

Data Index: 718549 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.5751. Min Act: -0.0002

Data Index: 302005 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.5339. Min Act: -0.0002

Data Index: 70906 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 3.0086. Min Range: -3.0086

Max Act: 2.5749. Min Act: -0.0002

Data Index: 1156418 (C4 (Web Text))

Max Activating Token Index: 595