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

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

Neuron 2586 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.9870. Min Act: -0.0000

Data Index: 537944 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.8141. Min Act: -0.0001

Data Index: 129489 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.9476. Min Act: -0.0000

Data Index: 198535 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 2.0115. Min Range: -2.0115

Max Act: 2.0115. Min Act: -0.0001

Data Index: 968705 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.7901. Min Act: -0.0000

Data Index: 822101 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.6343. Min Act: -0.0000

Data Index: 511883 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.6956. Min Act: -0.0000

Data Index: 365018 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.6883. Min Act: -0.0000

Data Index: 865973 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.6406. Min Act: -0.0000

Data Index: 135239 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.5346. Min Act: -0.0000

Data Index: 955988 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.5462. Min Act: -0.0000

Data Index: 335827 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.4918. Min Act: -0.0000

Data Index: 856457 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.5192. Min Act: -0.0000

Data Index: 151446 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.5263. Min Act: -0.0000

Data Index: 457728 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.5277. Min Act: -0.0000

Data Index: 1089752 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.4080. Min Act: -0.0001

Data Index: 1262629 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.3859. Min Act: -0.0001

Data Index: 879228 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.4634. Min Act: -0.0000

Data Index: 1204762 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.4178. Min Act: -0.0000

Data Index: 623959 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 2.0115. Min Range: -2.0115

Max Act: 1.4464. Min Act: -0.0000

Data Index: 480393 (C4 (Web Text))

Max Activating Token Index: 869