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

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

Neuron 4919 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0560. Min Range: -2.0560

Max Act: 2.0560. Min Act: -0.0000

Data Index: 319926 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.7622. Min Act: -0.0000

Data Index: 168083 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.6918. Min Act: -0.0000

Data Index: 704336 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.6952. Min Act: -0.0000

Data Index: 735555 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.5137. Min Act: -0.0000

Data Index: 715755 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.4856. Min Act: -0.0000

Data Index: 1056388 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.6396. Min Act: -0.0000

Data Index: 628957 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.6440. Min Act: -0.0000

Data Index: 198997 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.5524. Min Act: -0.0000

Data Index: 95897 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.5317. Min Act: -0.0000

Data Index: 276580 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.3874. Min Act: -0.0000

Data Index: 670228 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.3404. Min Act: -0.0000

Data Index: 1257638 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.6045. Min Act: -0.0000

Data Index: 929917 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.4467. Min Act: -0.0000

Data Index: 807212 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.4096. Min Act: -0.0000

Data Index: 268723 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.3827. Min Act: -0.0000

Data Index: 48472 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.3388. Min Act: -0.0000

Data Index: 98016 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.3300. Min Act: -0.0000

Data Index: 538400 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.3794. Min Act: -0.0000

Data Index: 957531 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 2.0560. Min Range: -2.0560

Max Act: 1.3285. Min Act: -0.0000

Data Index: 1264424 (C4 (Web Text))

Max Activating Token Index: 60