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

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

Neuron 3043 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2818. Min Range: -1.2818

Max Act: 1.2818. Min Act: -0.0001

Data Index: 68192 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 1.2818. Min Range: -1.2818

Max Act: 1.0089. Min Act: -0.0001

Data Index: 1200664 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 1.2818. Min Range: -1.2818

Max Act: 1.0019. Min Act: -0.0000

Data Index: 340813 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 1.2818. Min Range: -1.2818

Max Act: 1.0034. Min Act: -0.0001

Data Index: 68474 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1633057 (Python Code)

Max Activating Token Index: 761

Text #5

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.9217. Min Act: -0.0000

Data Index: 577178 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.9192. Min Act: -0.0000

Data Index: 693154 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1492712 (Python Code)

Max Activating Token Index: 786

Text #8

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.8537. Min Act: -0.0001

Data Index: 1212426 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.9324. Min Act: -0.0001

Data Index: 691385 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.8928. Min Act: -0.0000

Data Index: 1633491 (Python Code)

Max Activating Token Index: 750

Text #11

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1584964 (Python Code)

Max Activating Token Index: 703

Text #12

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.8790. Min Act: -0.0001

Data Index: 1607453 (Python Code)

Max Activating Token Index: 163

Text #13

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.9250. Min Act: -0.0000

Data Index: 1456596 (Python Code)

Max Activating Token Index: 795

Text #14

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1501230 (Python Code)

Max Activating Token Index: 484

Text #15

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.9414. Min Act: -0.0000

Data Index: 445017 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1100594 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1512786 (Python Code)

Max Activating Token Index: 341

Text #18

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1435972 (Python Code)

Max Activating Token Index: 513

Text #19

Max Range: 1.2818. Min Range: -1.2818

Max Act: 0.9107. Min Act: -0.0001

Data Index: 953342 (C4 (Web Text))

Max Activating Token Index: 563