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

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

Neuron 2255 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: 4.7094. Min Range: -4.7094

Max Act: 4.4013. Min Act: -0.0000

Data Index: 840386 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 4.7094. Min Range: -4.7094

Max Act: 4.7094. Min Act: -0.0000

Data Index: 5777 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 4.7094. Min Range: -4.7094

Max Act: 4.4815. Min Act: -0.0000

Data Index: 833068 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 4.7094. Min Range: -4.7094

Max Act: 4.2064. Min Act: -0.0000

Data Index: 80454 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 4.7094. Min Range: -4.7094

Max Act: 4.0615. Min Act: -0.0000

Data Index: 1075214 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.6639. Min Act: -0.0000

Data Index: 1136040 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.3023. Min Act: -0.0000

Data Index: 553394 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.7747. Min Act: -0.0000

Data Index: 577560 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.6467. Min Act: -0.0000

Data Index: 1127065 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.8316. Min Act: -0.0000

Data Index: 160335 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.8174. Min Act: -0.0000

Data Index: 600916 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.7473. Min Act: -0.0000

Data Index: 727405 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.5699. Min Act: -0.0000

Data Index: 534830 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.3799. Min Act: -0.0000

Data Index: 166552 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.6875. Min Act: -0.0000

Data Index: 791091 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.5223. Min Act: -0.0000

Data Index: 250557 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.3178. Min Act: -0.0001

Data Index: 932981 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.3886. Min Act: -0.0000

Data Index: 1020 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.3171. Min Act: -0.0000

Data Index: 31264 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 4.7094. Min Range: -4.7094

Max Act: 3.3527. Min Act: -0.0000

Data Index: 639619 (C4 (Web Text))

Max Activating Token Index: 685