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

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

Neuron 4670 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.5652. Min Act: -0.0000

Data Index: 1189930 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.5840. Min Act: -0.0000

Data Index: 526645 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.4974. Min Act: -0.0000

Data Index: 574448 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.4069. Min Act: -0.0001

Data Index: 40143 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.4163. Min Act: -0.0000

Data Index: 763088 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.2462. Min Act: -0.0000

Data Index: 931804 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.3737. Min Act: -0.0000

Data Index: 905342 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.2671. Min Act: -0.0000

Data Index: 655413 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.3879. Min Act: -0.0000

Data Index: 1002324 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.2207. Min Act: -0.0000

Data Index: 921911 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.2854. Min Act: -0.0000

Data Index: 1071071 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.2499. Min Act: -0.0000

Data Index: 1128720 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.2108. Min Act: -0.0001

Data Index: 442932 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.2193. Min Act: -0.0000

Data Index: 229468 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.2106. Min Act: -0.0001

Data Index: 743658 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.1490. Min Act: -0.0000

Data Index: 89568 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.2698. Min Act: -0.0000

Data Index: 200121 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.1672. Min Act: -0.0000

Data Index: 21560 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.2015. Min Act: -0.0000

Data Index: 861005 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 1.5840. Min Range: -1.5840

Max Act: 1.2257. Min Act: -0.0001

Data Index: 708665 (C4 (Web Text))

Max Activating Token Index: 624