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

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

Neuron 3043 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1100695 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1322588 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1267. Min Act: -0.0000

Data Index: 714204 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1084. Min Act: -0.0001

Data Index: 249783 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1084. Min Act: -0.0001

Data Index: 1128085 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1041436 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0939. Min Act: -0.0001

Data Index: 488058 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0934. Min Act: -0.0001

Data Index: 1153483 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0984. Min Act: -0.0001

Data Index: 222563 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1064384 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0896. Min Act: -0.0000

Data Index: 364648 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0954. Min Act: -0.0001

Data Index: 620024 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0907. Min Act: -0.0001

Data Index: 760645 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0897. Min Act: -0.0000

Data Index: 748334 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1283081 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1068786 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0821. Min Act: -0.0001

Data Index: 515824 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0844. Min Act: -0.0000

Data Index: 213541 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0837. Min Act: -0.0000

Data Index: 523836 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0837. Min Act: -0.0001

Data Index: 89040 (C4 (Web Text))

Max Activating Token Index: 719