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

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

Neuron 5750 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: 0.1224. Min Range: -0.1224

Max Act: 0.1224. Min Act: -0.0001

Data Index: 7373 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1082. Min Act: -0.0001

Data Index: 977890 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1107. Min Act: -0.0001

Data Index: 161388 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1024. Min Act: -0.0001

Data Index: 640894 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1084020 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0908. Min Act: -0.0001

Data Index: 848340 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1044. Min Act: -0.0001

Data Index: 916931 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0924. Min Act: -0.0001

Data Index: 297827 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0984. Min Act: -0.0001

Data Index: 90089 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0897. Min Act: -0.0001

Data Index: 178863 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0814. Min Act: -0.0001

Data Index: 705781 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0977. Min Act: -0.0001

Data Index: 946036 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0858. Min Act: -0.0001

Data Index: 317563 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0914. Min Act: -0.0001

Data Index: 450059 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0806. Min Act: -0.0001

Data Index: 754291 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0904. Min Act: -0.0001

Data Index: 356627 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0952. Min Act: -0.0001

Data Index: 328409 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0862. Min Act: -0.0001

Data Index: 546236 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0953. Min Act: -0.0001

Data Index: 444271 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1091836 (C4 (Web Text))

Max Activating Token Index: 159