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

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

Neuron 1274 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7618. Min Act: -0.0003

Data Index: 582193 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7705. Min Act: -0.0002

Data Index: 404792 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7026. Min Act: -0.0003

Data Index: 583280 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6906. Min Act: -0.0003

Data Index: 1165561 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6879. Min Act: -0.0002

Data Index: 927888 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6686. Min Act: -0.0003

Data Index: 223536 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6436. Min Act: -0.0002

Data Index: 959686 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6635. Min Act: -0.0002

Data Index: 953047 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6454. Min Act: -0.0002

Data Index: 1251242 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6660. Min Act: -0.0003

Data Index: 974972 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6852. Min Act: -0.0002

Data Index: 729394 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6645. Min Act: -0.0002

Data Index: 374747 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6328. Min Act: -0.0003

Data Index: 1179855 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6173. Min Act: -0.0002

Data Index: 194510 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6094. Min Act: -0.0003

Data Index: 1189612 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5775. Min Act: -0.0003

Data Index: 1158063 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5940. Min Act: -0.0003

Data Index: 481418 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5778. Min Act: -0.0003

Data Index: 580127 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5946. Min Act: -0.0003

Data Index: 1279359 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5918. Min Act: -0.0003

Data Index: 1311267 (C4 (Web Text))

Max Activating Token Index: 351