Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 438 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1105. Min Act: -0.0001

Data Index: 601747 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1228892 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0724. Min Act: -0.0001

Data Index: 321309 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0672. Min Act: -0.0001

Data Index: 765402 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0674. Min Act: -0.0001

Data Index: 195015 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0643. Min Act: -0.0001

Data Index: 376282 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0667. Min Act: -0.0001

Data Index: 792010 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0656. Min Act: -0.0001

Data Index: 614269 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1028069 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0649. Min Act: -0.0001

Data Index: 285108 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0670. Min Act: -0.0001

Data Index: 955263 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0608. Min Act: -0.0001

Data Index: 56615 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0620. Min Act: -0.0001

Data Index: 929954 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0618. Min Act: -0.0001

Data Index: 872246 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0613. Min Act: -0.0001

Data Index: 891184 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1347250 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0611. Min Act: -0.0001

Data Index: 92822 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0579. Min Act: -0.0001

Data Index: 242661 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0601. Min Act: -0.0001

Data Index: 264143 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0594. Min Act: -0.0001

Data Index: 246696 (C4 (Web Text))

Max Activating Token Index: 22