Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3388 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0277. Min Range: -2.0277

Max Act: 2.0277. Min Act: -0.0000

Data Index: 374212 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.9887. Min Act: -0.0000

Data Index: 1318629 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.7673. Min Act: -0.0000

Data Index: 620800 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.5594. Min Act: -0.0000

Data Index: 487984 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.5132. Min Act: -0.0000

Data Index: 813340 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.6345. Min Act: -0.0000

Data Index: 1334130 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.5911. Min Act: -0.0000

Data Index: 1091992 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.4034. Min Act: -0.0000

Data Index: 70148 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.3329. Min Act: -0.0000

Data Index: 996342 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.3171. Min Act: -0.0000

Data Index: 1298881 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.3644. Min Act: -0.0000

Data Index: 719744 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.4003. Min Act: -0.0000

Data Index: 298224 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.3229. Min Act: -0.0000

Data Index: 505555 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.2377. Min Act: -0.0000

Data Index: 18452 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.2668. Min Act: -0.0000

Data Index: 351477 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.1917. Min Act: -0.0000

Data Index: 454103 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.1791. Min Act: -0.0000

Data Index: 988279 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.1429. Min Act: -0.0000

Data Index: 913622 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.1526. Min Act: -0.0000

Data Index: 1093865 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 2.0277. Min Range: -2.0277

Max Act: 1.2042. Min Act: -0.0000

Data Index: 217753 (C4 (Web Text))

Max Activating Token Index: 141