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

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

Neuron 545 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.9860. Min Act: -0.0000

Data Index: 238182 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.9641. Min Act: -0.0000

Data Index: 365053 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.4652. Min Act: -0.0000

Data Index: 943672 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.5793. Min Act: -0.0000

Data Index: 1208805 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.6350. Min Act: -0.0000

Data Index: 528789 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.3939. Min Act: -0.0000

Data Index: 1331911 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.2682. Min Act: -0.0000

Data Index: 123774 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.3320. Min Act: -0.0000

Data Index: 979874 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.2976. Min Act: -0.0000

Data Index: 72876 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.2699. Min Act: -0.0000

Data Index: 356830 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.2904. Min Act: -0.0000

Data Index: 792104 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.2165. Min Act: -0.0000

Data Index: 915461 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.2262. Min Act: -0.0000

Data Index: 658335 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.0639. Min Act: -0.0000

Data Index: 26178 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.1107. Min Act: -0.0000

Data Index: 429006 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.1040. Min Act: -0.0000

Data Index: 1017871 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.2671. Min Act: -0.0000

Data Index: 827359 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.1012. Min Act: -0.0000

Data Index: 748732 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.0990. Min Act: -0.0000

Data Index: 1332327 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 3.9860. Min Range: -3.9860

Max Act: 3.0510. Min Act: -0.0000

Data Index: 1139103 (C4 (Web Text))

Max Activating Token Index: 763