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

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

Neuron 1493 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0972. Min Act: -0.0002

Data Index: 419301 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0952. Min Act: -0.0002

Data Index: 415367 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0961. Min Act: -0.0002

Data Index: 1211856 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0938. Min Act: -0.0002

Data Index: 870966 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0948. Min Act: -0.0002

Data Index: 937538 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1117075 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0957. Min Act: -0.0002

Data Index: 988462 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0921. Min Act: -0.0002

Data Index: 73010 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0918. Min Act: -0.0002

Data Index: 604153 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0943. Min Act: -0.0002

Data Index: 114708 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0919. Min Act: -0.0002

Data Index: 969622 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0904. Min Act: -0.0002

Data Index: 670685 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0900. Min Act: -0.0002

Data Index: 216927 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1297659 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0885. Min Act: -0.0002

Data Index: 891083 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0884. Min Act: -0.0002

Data Index: 827910 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0899. Min Act: -0.0002

Data Index: 480891 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0901. Min Act: -0.0002

Data Index: 132774 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0884. Min Act: -0.0002

Data Index: 924620 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0887. Min Act: -0.0002

Data Index: 182214 (C4 (Web Text))

Max Activating Token Index: 691