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

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

Neuron 4737 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0839. Min Range: -2.0839

Max Act: 2.0839. Min Act: -0.0000

Data Index: 152095 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.9672. Min Act: -0.0000

Data Index: 910492 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.8641. Min Act: -0.0000

Data Index: 283984 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.8317. Min Act: -0.0000

Data Index: 243227 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.2680. Min Act: -0.0000

Data Index: 430609 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.1179. Min Act: -0.0000

Data Index: 357900 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 2.0839. Min Range: -2.0839

Max Act: 0.8820. Min Act: -0.0000

Data Index: 772111 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 2.0839. Min Range: -2.0839

Max Act: 0.7405. Min Act: -0.0000

Data Index: 281968 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.1309. Min Act: -0.0000

Data Index: 640037 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 2.0839. Min Range: -2.0839

Max Act: 0.8467. Min Act: -0.0000

Data Index: 459572 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 2.0839. Min Range: -2.0839

Max Act: 0.8748. Min Act: -0.0000

Data Index: 658638 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 2.0839. Min Range: -2.0839

Max Act: 0.7753. Min Act: -0.0000

Data Index: 929101 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 2.0839. Min Range: -2.0839

Max Act: 0.8417. Min Act: -0.0000

Data Index: 713434 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 2.0839. Min Range: -2.0839

Max Act: 0.6589. Min Act: -0.0000

Data Index: 566956 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 2.0839. Min Range: -2.0839

Max Act: 0.8093. Min Act: -0.0000

Data Index: 409705 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 2.0839. Min Range: -2.0839

Max Act: 0.6550. Min Act: -0.0000

Data Index: 897173 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 2.0839. Min Range: -2.0839

Max Act: 0.7940. Min Act: -0.0000

Data Index: 371502 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 2.0839. Min Range: -2.0839

Max Act: 0.7418. Min Act: -0.0000

Data Index: 82116 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 2.0839. Min Range: -2.0839

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1005007 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 2.0839. Min Range: -2.0839

Max Act: 0.6478. Min Act: -0.0000

Data Index: 327952 (C4 (Web Text))

Max Activating Token Index: 342