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

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

Neuron 5113 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.6961. Min Act: -0.0000

Data Index: 170766 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.7848. Min Act: -0.0000

Data Index: 54582 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.6902. Min Act: -0.0000

Data Index: 843970 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1212111 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.7264. Min Act: -0.0000

Data Index: 959511 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.6070. Min Act: -0.0000

Data Index: 592267 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.5801. Min Act: -0.0000

Data Index: 450852 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4876. Min Act: -0.0000

Data Index: 339967 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1593014 (Python Code)

Max Activating Token Index: 279

Text #9

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.5569. Min Act: -0.0000

Data Index: 694994 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1245781 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.5218. Min Act: -0.0000

Data Index: 87667 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1351988 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1199053 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4671. Min Act: -0.0000

Data Index: 585763 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4711. Min Act: -0.0000

Data Index: 531157 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4278. Min Act: -0.0000

Data Index: 1538486 (Python Code)

Max Activating Token Index: 933

Text #17

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4520. Min Act: -0.0000

Data Index: 908374 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4646. Min Act: -0.0000

Data Index: 578821 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.7848. Min Range: -0.7848

Max Act: 0.4326. Min Act: -0.0000

Data Index: 473306 (C4 (Web Text))

Max Activating Token Index: 133