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

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

Neuron 4839 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1208024 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2681. Min Act: -0.0000

Data Index: 190110 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1055969 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2494. Min Act: -0.0000

Data Index: 889203 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2466. Min Act: -0.0000

Data Index: 963572 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2312. Min Act: -0.0000

Data Index: 347086 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1328046 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2254. Min Act: -0.0000

Data Index: 305157 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2123. Min Act: -0.0000

Data Index: 79620 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2195. Min Act: -0.0000

Data Index: 846002 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1142143 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1060260 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1155041 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2067. Min Act: -0.0000

Data Index: 978976 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2118. Min Act: -0.0000

Data Index: 322506 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2063. Min Act: -0.0000

Data Index: 901350 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1964. Min Act: -0.0000

Data Index: 848866 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1254928 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.2001. Min Act: -0.0000

Data Index: 615251 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.2867. Min Range: -0.2867

Max Act: 0.1956. Min Act: -0.0000

Data Index: 178876 (C4 (Web Text))

Max Activating Token Index: 694