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

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

Neuron 4573 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.8919. Min Act: -0.0001

Data Index: 559317 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.8731. Min Act: -0.0001

Data Index: 355099 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.8937. Min Act: -0.0000

Data Index: 778274 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.8456. Min Act: -0.0000

Data Index: 1120311 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.8382. Min Act: -0.0000

Data Index: 190467 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.7830. Min Act: -0.0001

Data Index: 477209 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.7818. Min Act: -0.0001

Data Index: 1132820 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.7717. Min Act: -0.0001

Data Index: 659554 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.8143. Min Act: -0.0001

Data Index: 233449 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.8005. Min Act: -0.0001

Data Index: 1190940 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.8019. Min Act: -0.0001

Data Index: 900766 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.8022. Min Act: -0.0001

Data Index: 39017 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.7160. Min Act: -0.0001

Data Index: 1219801 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.6907. Min Act: -0.0001

Data Index: 82069 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.6950. Min Act: -0.0001

Data Index: 875946 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.6830. Min Act: -0.0001

Data Index: 922308 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.6254. Min Act: -0.0001

Data Index: 1147587 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.7051. Min Act: -0.0001

Data Index: 109581 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.6701. Min Act: -0.0001

Data Index: 1147260 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.8937. Min Range: -0.8937

Max Act: 0.6723. Min Act: -0.0000

Data Index: 986304 (C4 (Web Text))

Max Activating Token Index: 677