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

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

Neuron 3333 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1117882 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.6441. Min Act: -0.0000

Data Index: 701329 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.6370. Min Act: -0.0000

Data Index: 948147 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1220533 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.6268. Min Act: -0.0000

Data Index: 803249 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.6046. Min Act: -0.0000

Data Index: 788710 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1271287 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5866. Min Act: -0.0000

Data Index: 644138 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.6064. Min Act: -0.0000

Data Index: 29511 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1111438 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5381. Min Act: -0.0000

Data Index: 1018637 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5728. Min Act: -0.0000

Data Index: 292486 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5820. Min Act: -0.0000

Data Index: 319811 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5489. Min Act: -0.0000

Data Index: 139491 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5623. Min Act: -0.0000

Data Index: 711686 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5609. Min Act: -0.0000

Data Index: 926275 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5612. Min Act: -0.0000

Data Index: 674790 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5108. Min Act: -0.0001

Data Index: 1062527 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5577. Min Act: -0.0000

Data Index: 958726 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4846. Min Act: -0.0000

Data Index: 108743 (C4 (Web Text))

Max Activating Token Index: 194