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

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

Neuron 3919 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.7439. Min Act: -0.0001

Data Index: 1300762 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5792. Min Act: -0.0000

Data Index: 814802 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5315. Min Act: -0.0001

Data Index: 1522513 (Python Code)

Max Activating Token Index: 866

Text #3

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5043. Min Act: -0.0001

Data Index: 827218 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5353. Min Act: -0.0001

Data Index: 746621 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5069. Min Act: -0.0001

Data Index: 421817 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4938. Min Act: -0.0001

Data Index: 159801 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4746. Min Act: -0.0001

Data Index: 1061949 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4864. Min Act: -0.0001

Data Index: 1152705 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5038. Min Act: -0.0001

Data Index: 757208 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4630. Min Act: -0.0001

Data Index: 576532 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4771. Min Act: -0.0001

Data Index: 1579207 (Python Code)

Max Activating Token Index: 173

Text #12

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4612. Min Act: -0.0001

Data Index: 1065938 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4737. Min Act: -0.0001

Data Index: 470422 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4945. Min Act: -0.0001

Data Index: 45155 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4681. Min Act: -0.0001

Data Index: 1244740 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4833. Min Act: -0.0001

Data Index: 1062948 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5060. Min Act: -0.0001

Data Index: 1168785 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4438. Min Act: -0.0001

Data Index: 665635 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4692. Min Act: -0.0001

Data Index: 1434804 (Python Code)

Max Activating Token Index: 266