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

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

Neuron 943 in Layer 0

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: 1.2055. Min Range: -1.2055

Max Act: 1.2055. Min Act: -0.0001

Data Index: 1003626 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1626. Min Act: -0.0001

Data Index: 1277680 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1563. Min Act: -0.0001

Data Index: 706343 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1500. Min Act: -0.0001

Data Index: 1214971 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1621. Min Act: -0.0001

Data Index: 784873 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1436. Min Act: -0.0001

Data Index: 266506 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1295. Min Act: -0.0001

Data Index: 1081589 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1482. Min Act: -0.0001

Data Index: 534239 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1220. Min Act: -0.0001

Data Index: 1159221 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1032. Min Act: -0.0001

Data Index: 204549 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1087. Min Act: -0.0001

Data Index: 683854 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.0911. Min Act: -0.0002

Data Index: 818182 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1163. Min Act: -0.0001

Data Index: 1338923 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.0914. Min Act: -0.0001

Data Index: 984692 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1026. Min Act: -0.0001

Data Index: 273504 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1071. Min Act: -0.0001

Data Index: 1241493 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.0900. Min Act: -0.0001

Data Index: 24465 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1070. Min Act: -0.0001

Data Index: 1143551 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.0873. Min Act: -0.0001

Data Index: 664279 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.0884. Min Act: -0.0001

Data Index: 1319513 (C4 (Web Text))

Max Activating Token Index: 6