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

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

Neuron 1174 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0120. Min Act: -0.0006

Data Index: 615993 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0120. Min Act: -0.0006

Data Index: 964602 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0117. Min Act: -0.0006

Data Index: 592260 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0114. Min Act: -0.0006

Data Index: 985565 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0113. Min Act: -0.0006

Data Index: 961296 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1077625 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0110. Min Act: -0.0006

Data Index: 955947 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0110. Min Act: -0.0006

Data Index: 292663 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1326794 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0105. Min Act: -0.0006

Data Index: 325035 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0105. Min Act: -0.0006

Data Index: 751358 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0103. Min Act: -0.0006

Data Index: 57480 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0106. Min Act: -0.0006

Data Index: 860961 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0103. Min Act: -0.0006

Data Index: 153090 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0111. Min Act: -0.0006

Data Index: 840253 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0105. Min Act: -0.0006

Data Index: 899100 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0103. Min Act: -0.0006

Data Index: 520738 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0106. Min Act: -0.0006

Data Index: 205612 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1303032 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1309659 (C4 (Web Text))

Max Activating Token Index: 244