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

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

Neuron 2050 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.5200. Min Act: -0.0000

Data Index: 133039 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4989. Min Act: -0.0000

Data Index: 782372 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.5329. Min Act: -0.0000

Data Index: 645087 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4832. Min Act: -0.0000

Data Index: 739546 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4803. Min Act: -0.0000

Data Index: 141884 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4758. Min Act: -0.0000

Data Index: 570615 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.5062. Min Act: -0.0000

Data Index: 755142 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1040838 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4662. Min Act: -0.0000

Data Index: 252708 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1073058 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4249. Min Act: -0.0000

Data Index: 624829 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4226. Min Act: -0.0000

Data Index: 316520 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3925. Min Act: -0.0000

Data Index: 301908 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1001244 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4518. Min Act: -0.0000

Data Index: 58125 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4434. Min Act: -0.0000

Data Index: 563997 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1099057 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4341. Min Act: -0.0000

Data Index: 625468 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4278. Min Act: -0.0000

Data Index: 1273800 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3984. Min Act: -0.0000

Data Index: 794285 (C4 (Web Text))

Max Activating Token Index: 839