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

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

Neuron 3262 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1674. Min Act: -0.0001

Data Index: 866390 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1576. Min Act: -0.0001

Data Index: 688445 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1566. Min Act: -0.0001

Data Index: 645613 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1328. Min Act: -0.0001

Data Index: 119315 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1561. Min Act: -0.0001

Data Index: 334758 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1557. Min Act: -0.0001

Data Index: 875943 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1254. Min Act: -0.0001

Data Index: 723755 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1332. Min Act: -0.0001

Data Index: 181518 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1114. Min Act: -0.0001

Data Index: 549214 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1080. Min Act: -0.0001

Data Index: 381247 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1335626 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1000. Min Act: -0.0001

Data Index: 768608 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1065. Min Act: -0.0001

Data Index: 390548 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1178843 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1019. Min Act: -0.0001

Data Index: 701116 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1055. Min Act: -0.0001

Data Index: 756115 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1012. Min Act: -0.0001

Data Index: 467686 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1000. Min Act: -0.0001

Data Index: 12020 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1028. Min Act: -0.0001

Data Index: 998688 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.0950. Min Act: -0.0001

Data Index: 7095 (C4 (Web Text))

Max Activating Token Index: 135