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

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

Neuron 3283 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5131. Min Range: -4.5131

Max Act: 4.2144. Min Act: -0.0000

Data Index: 488956 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 4.5131. Min Range: -4.5131

Max Act: 4.5131. Min Act: -0.0000

Data Index: 584469 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.9787. Min Act: -0.0000

Data Index: 121429 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 4.5131. Min Range: -4.5131

Max Act: 4.1036. Min Act: -0.0000

Data Index: 352423 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.8733. Min Act: -0.0000

Data Index: 741853 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.9990. Min Act: -0.0000

Data Index: 373851 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.6171. Min Act: -0.0000

Data Index: 125845 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.7566. Min Act: -0.0000

Data Index: 407154 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.5952. Min Act: -0.0000

Data Index: 970364 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.4216. Min Act: -0.0000

Data Index: 409962 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.5807. Min Act: -0.0000

Data Index: 7583 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.5575. Min Act: -0.0000

Data Index: 1343650 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.4208. Min Act: -0.0000

Data Index: 37049 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.5435. Min Act: -0.0000

Data Index: 1108760 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.3775. Min Act: -0.0000

Data Index: 765196 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.3368. Min Act: -0.0000

Data Index: 1106072 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.6902. Min Act: -0.0000

Data Index: 1140374 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.6216. Min Act: -0.0000

Data Index: 1344723 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.4572. Min Act: -0.0000

Data Index: 84683 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 4.5131. Min Range: -4.5131

Max Act: 3.5769. Min Act: -0.0000

Data Index: 1345657 (C4 (Web Text))

Max Activating Token Index: 290