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

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

Neuron 5857 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: 0.5404. Min Range: -0.5404

Max Act: 0.5139. Min Act: -0.0001

Data Index: 657150 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.5134. Min Act: -0.0001

Data Index: 821604 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.5404. Min Act: -0.0001

Data Index: 380908 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.4376. Min Act: -0.0001

Data Index: 889199 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.4435. Min Act: -0.0001

Data Index: 615465 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.4053. Min Act: -0.0001

Data Index: 808508 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.4194. Min Act: -0.0001

Data Index: 233389 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.4186. Min Act: -0.0001

Data Index: 339001 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3997. Min Act: -0.0001

Data Index: 105258 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3714. Min Act: -0.0001

Data Index: 270318 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.4000. Min Act: -0.0001

Data Index: 474955 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.4100. Min Act: -0.0001

Data Index: 751230 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3867. Min Act: -0.0001

Data Index: 734191 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3743. Min Act: -0.0001

Data Index: 92211 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3919. Min Act: -0.0001

Data Index: 193697 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3778. Min Act: -0.0001

Data Index: 25412 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3852. Min Act: -0.0001

Data Index: 1048714 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3710. Min Act: -0.0001

Data Index: 1262519 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3946. Min Act: -0.0001

Data Index: 616404 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3689. Min Act: -0.0001

Data Index: 1004644 (C4 (Web Text))

Max Activating Token Index: 76