Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1000 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0752. Min Act: -0.0005

Data Index: 411518 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0610. Min Act: -0.0005

Data Index: 786351 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0607. Min Act: -0.0005

Data Index: 946961 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0591. Min Act: -0.0005

Data Index: 167928 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0569. Min Act: -0.0005

Data Index: 534662 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0552. Min Act: -0.0005

Data Index: 950144 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0545. Min Act: -0.0005

Data Index: 1321281 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0542. Min Act: -0.0005

Data Index: 1124292 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0526. Min Act: -0.0005

Data Index: 927655 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0537. Min Act: -0.0005

Data Index: 858672 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0518. Min Act: -0.0005

Data Index: 846215 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0523. Min Act: -0.0005

Data Index: 174750 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0512. Min Act: -0.0004

Data Index: 969984 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0543. Min Act: -0.0005

Data Index: 181275 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0509. Min Act: -0.0005

Data Index: 93920 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0495. Min Act: -0.0005

Data Index: 394732 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0516. Min Act: -0.0005

Data Index: 832170 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0503. Min Act: -0.0005

Data Index: 855176 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0513. Min Act: -0.0005

Data Index: 459050 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0503. Min Act: -0.0005

Data Index: 1308626 (C4 (Web Text))

Max Activating Token Index: 10