Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 358 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1224. Min Act: -0.0002

Data Index: 126100 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1181. Min Act: -0.0001

Data Index: 18961 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1208. Min Act: -0.0001

Data Index: 383092 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1112. Min Act: -0.0001

Data Index: 177832 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1062. Min Act: -0.0001

Data Index: 841039 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1196244 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1082. Min Act: -0.0001

Data Index: 134090 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1016. Min Act: -0.0001

Data Index: 362955 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1000. Min Act: -0.0001

Data Index: 338687 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0929. Min Act: -0.0001

Data Index: 994647 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1050. Min Act: -0.0001

Data Index: 577593 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0926. Min Act: -0.0001

Data Index: 516415 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0949. Min Act: -0.0001

Data Index: 981953 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0989. Min Act: -0.0001

Data Index: 404233 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0988. Min Act: -0.0001

Data Index: 773988 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0900. Min Act: -0.0001

Data Index: 501879 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0892. Min Act: -0.0001

Data Index: 337142 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0918. Min Act: -0.0001

Data Index: 647436 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1255184 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0870. Min Act: -0.0001

Data Index: 512953 (C4 (Web Text))

Max Activating Token Index: 122