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

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

Neuron 1868 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.3808. Min Act: -0.0001

Data Index: 759881 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.2067. Min Act: -0.0001

Data Index: 673903 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1823. Min Act: -0.0001

Data Index: 1230055 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1460. Min Act: -0.0001

Data Index: 477531 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1686. Min Act: -0.0001

Data Index: 909503 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1466. Min Act: -0.0001

Data Index: 1113496 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1242. Min Act: -0.0001

Data Index: 1111392 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.0485. Min Act: -0.0001

Data Index: 755858 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.0448. Min Act: -0.0001

Data Index: 487421 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1082. Min Act: -0.0001

Data Index: 864295 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1064. Min Act: -0.0001

Data Index: 840092 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.0634. Min Act: -0.0001

Data Index: 507469 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.9566. Min Act: -0.0001

Data Index: 624300 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.0119. Min Act: -0.0001

Data Index: 219114 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.0365. Min Act: -0.0001

Data Index: 212821 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.1087. Min Act: -0.0001

Data Index: 1105208 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.0526. Min Act: -0.0001

Data Index: 112447 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.0718. Min Act: -0.0001

Data Index: 1191900 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 1.3808. Min Range: -1.3808

Max Act: 0.9969. Min Act: -0.0001

Data Index: 969064 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 1.3808. Min Range: -1.3808

Max Act: 1.0195. Min Act: -0.0001

Data Index: 720176 (C4 (Web Text))

Max Activating Token Index: 14