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

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

Neuron 706 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0710. Min Range: -8.0710

Max Act: 8.0710. Min Act: -0.0000

Data Index: 468682 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 8.0710. Min Range: -8.0710

Max Act: 7.5520. Min Act: -0.0000

Data Index: 773655 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 8.0710. Min Range: -8.0710

Max Act: 7.5704. Min Act: -0.0000

Data Index: 677528 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 8.0710. Min Range: -8.0710

Max Act: 7.1840. Min Act: -0.0000

Data Index: 763008 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 8.0710. Min Range: -8.0710

Max Act: 7.3859. Min Act: -0.0000

Data Index: 1082110 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 8.0710. Min Range: -8.0710

Max Act: 7.1843. Min Act: -0.0000

Data Index: 130949 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 8.0710. Min Range: -8.0710

Max Act: 7.3445. Min Act: -0.0000

Data Index: 1144951 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 8.0710. Min Range: -8.0710

Max Act: 7.1772. Min Act: -0.0000

Data Index: 438919 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 8.0710. Min Range: -8.0710

Max Act: 6.8589. Min Act: -0.0000

Data Index: 866872 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 8.0710. Min Range: -8.0710

Max Act: 5.1331. Min Act: -0.0000

Data Index: 1279173 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 8.0710. Min Range: -8.0710

Max Act: 5.0736. Min Act: -0.0000

Data Index: 1125274 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 8.0710. Min Range: -8.0710

Max Act: 5.3546. Min Act: -0.0000

Data Index: 1251838 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 8.0710. Min Range: -8.0710

Max Act: 4.5296. Min Act: -0.0000

Data Index: 470857 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 8.0710. Min Range: -8.0710

Max Act: 4.4463. Min Act: -0.0000

Data Index: 711168 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 8.0710. Min Range: -8.0710

Max Act: 4.4055. Min Act: -0.0000

Data Index: 941948 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 8.0710. Min Range: -8.0710

Max Act: 4.3637. Min Act: -0.0000

Data Index: 235450 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 8.0710. Min Range: -8.0710

Max Act: 4.3069. Min Act: -0.0000

Data Index: 468742 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 8.0710. Min Range: -8.0710

Max Act: 4.2741. Min Act: -0.0000

Data Index: 849130 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 8.0710. Min Range: -8.0710

Max Act: 4.0666. Min Act: -0.0000

Data Index: 226817 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 8.0710. Min Range: -8.0710

Max Act: 4.0033. Min Act: -0.0000

Data Index: 654539 (C4 (Web Text))

Max Activating Token Index: 523