Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 229 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1228498 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1222. Min Act: -0.0002

Data Index: 158838 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1091. Min Act: -0.0002

Data Index: 505434 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1113. Min Act: -0.0002

Data Index: 1262488 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1062. Min Act: -0.0002

Data Index: 509591 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1062. Min Act: -0.0002

Data Index: 664946 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0956. Min Act: -0.0002

Data Index: 681524 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1027591 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1301553 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0982. Min Act: -0.0002

Data Index: 104510 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1204708 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0949. Min Act: -0.0002

Data Index: 443061 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1210237 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1250501 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0903. Min Act: -0.0002

Data Index: 847516 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0919. Min Act: -0.0002

Data Index: 540489 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0961. Min Act: -0.0002

Data Index: 599915 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0884. Min Act: -0.0002

Data Index: 569674 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1381599 (Python Code)

Max Activating Token Index: 910

Text #19

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0994. Min Act: -0.0002

Data Index: 914990 (C4 (Web Text))

Max Activating Token Index: 555