Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 611 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.6841. Min Act: -0.0001

Data Index: 198686 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.6582. Min Act: -0.0001

Data Index: 1150749 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4871. Min Act: -0.0001

Data Index: 1096856 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5851. Min Act: -0.0001

Data Index: 146449 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5931. Min Act: -0.0001

Data Index: 437492 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.6118. Min Act: -0.0001

Data Index: 839487 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.4979. Min Act: -0.0001

Data Index: 898010 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5895. Min Act: -0.0001

Data Index: 928269 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5455. Min Act: -0.0001

Data Index: 1050128 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5791. Min Act: -0.0001

Data Index: 1033538 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5816. Min Act: -0.0001

Data Index: 1309996 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5078. Min Act: -0.0001

Data Index: 874638 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5617. Min Act: -0.0001

Data Index: 969659 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5636. Min Act: -0.0001

Data Index: 1173398 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5530. Min Act: -0.0001

Data Index: 937572 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5581. Min Act: -0.0001

Data Index: 74251 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5521. Min Act: -0.0001

Data Index: 328971 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5938. Min Act: -0.0001

Data Index: 585707 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5735. Min Act: -0.0001

Data Index: 871710 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5699. Min Act: -0.0001

Data Index: 1084652 (C4 (Web Text))

Max Activating Token Index: 18