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

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

Neuron 971 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1243. Min Act: -0.0001

Data Index: 434805 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1083. Min Act: -0.0001

Data Index: 119047 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1043809 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1105. Min Act: -0.0001

Data Index: 214605 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1029. Min Act: -0.0001

Data Index: 890636 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1066523 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1061111 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1043. Min Act: -0.0002

Data Index: 414191 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1157638 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1013. Min Act: -0.0001

Data Index: 909786 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1006. Min Act: -0.0001

Data Index: 886357 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1033. Min Act: -0.0001

Data Index: 549961 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1190372 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0915. Min Act: -0.0001

Data Index: 182415 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1204013 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1357752 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0978. Min Act: -0.0001

Data Index: 402959 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0949. Min Act: -0.0001

Data Index: 469749 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0947. Min Act: -0.0001

Data Index: 903601 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1011. Min Act: -0.0001

Data Index: 401786 (C4 (Web Text))

Max Activating Token Index: 290