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

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

Neuron 2272 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5482. Min Range: -2.5482

Max Act: 2.5482. Min Act: -0.0000

Data Index: 700151 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 2.5482. Min Range: -2.5482

Max Act: 2.4564. Min Act: -0.0000

Data Index: 229344 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 2.5482. Min Range: -2.5482

Max Act: 2.1100. Min Act: -0.0000

Data Index: 723774 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 2.5482. Min Range: -2.5482

Max Act: 2.2863. Min Act: -0.0000

Data Index: 1214797 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 2.5482. Min Range: -2.5482

Max Act: 2.1171. Min Act: -0.0000

Data Index: 347827 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 2.5482. Min Range: -2.5482

Max Act: 2.0501. Min Act: -0.0000

Data Index: 733431 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 2.5482. Min Range: -2.5482

Max Act: 1.9158. Min Act: -0.0000

Data Index: 987507 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 2.5482. Min Range: -2.5482

Max Act: 1.5998. Min Act: -0.0000

Data Index: 550811 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 2.5482. Min Range: -2.5482

Max Act: 1.7422. Min Act: -0.0000

Data Index: 578597 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 2.5482. Min Range: -2.5482

Max Act: 1.8046. Min Act: -0.0000

Data Index: 990147 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 2.5482. Min Range: -2.5482

Max Act: 1.7937. Min Act: -0.0000

Data Index: 488856 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 2.5482. Min Range: -2.5482

Max Act: 1.7710. Min Act: -0.0000

Data Index: 607942 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 2.5482. Min Range: -2.5482

Max Act: 1.5962. Min Act: -0.0000

Data Index: 597349 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 2.5482. Min Range: -2.5482

Max Act: 1.6625. Min Act: -0.0000

Data Index: 1304366 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 2.5482. Min Range: -2.5482

Max Act: 1.6516. Min Act: -0.0000

Data Index: 970908 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 2.5482. Min Range: -2.5482

Max Act: 1.5588. Min Act: -0.0000

Data Index: 505220 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 2.5482. Min Range: -2.5482

Max Act: 1.7201. Min Act: -0.0000

Data Index: 604431 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 2.5482. Min Range: -2.5482

Max Act: 1.8083. Min Act: -0.0000

Data Index: 321632 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 2.5482. Min Range: -2.5482

Max Act: 1.6259. Min Act: -0.0000

Data Index: 850784 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 2.5482. Min Range: -2.5482

Max Act: 1.4422. Min Act: -0.0000

Data Index: 963751 (C4 (Web Text))

Max Activating Token Index: 391