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

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

Neuron 1928 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.6772. Min Act: -0.0001

Data Index: 511612 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.6166. Min Act: -0.0001

Data Index: 1053149 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.6016. Min Act: -0.0001

Data Index: 830713 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.6179. Min Act: -0.0001

Data Index: 1191554 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.6124. Min Act: -0.0001

Data Index: 577326 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5625. Min Act: -0.0001

Data Index: 9039 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5605. Min Act: -0.0001

Data Index: 843140 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5991. Min Act: -0.0001

Data Index: 1223485 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5901. Min Act: -0.0001

Data Index: 1199326 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.6050. Min Act: -0.0001

Data Index: 976997 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5703. Min Act: -0.0001

Data Index: 1078441 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5679. Min Act: -0.0001

Data Index: 1357921 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5567. Min Act: -0.0001

Data Index: 724602 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5570. Min Act: -0.0001

Data Index: 392139 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5733. Min Act: -0.0001

Data Index: 1329320 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5730. Min Act: -0.0001

Data Index: 1067341 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5513. Min Act: -0.0001

Data Index: 531236 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5559. Min Act: -0.0001

Data Index: 108393 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5549. Min Act: -0.0001

Data Index: 316554 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5328. Min Act: -0.0001

Data Index: 1070172 (C4 (Web Text))

Max Activating Token Index: 227