Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 40 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1218. Min Act: -0.0001

Data Index: 113417 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1111. Min Act: -0.0001

Data Index: 638006 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0976. Min Act: -0.0001

Data Index: 464431 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0921. Min Act: -0.0001

Data Index: 503774 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0921. Min Act: -0.0001

Data Index: 34267 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0956. Min Act: -0.0001

Data Index: 48425 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0864. Min Act: -0.0001

Data Index: 273739 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0887. Min Act: -0.0001

Data Index: 754910 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1052026 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0908. Min Act: -0.0001

Data Index: 447411 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0828. Min Act: -0.0001

Data Index: 1006280 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1266972 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1196499 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0771. Min Act: -0.0001

Data Index: 679982 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1150778 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0821. Min Act: -0.0001

Data Index: 337752 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0854. Min Act: -0.0001

Data Index: 298132 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0882. Min Act: -0.0001

Data Index: 1043008 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0816. Min Act: -0.0001

Data Index: 436686 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0869. Min Act: -0.0001

Data Index: 471023 (C4 (Web Text))

Max Activating Token Index: 758