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

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

Neuron 2505 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1478. Min Act: -0.0004

Data Index: 176874 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1536. Min Act: -0.0004

Data Index: 1434099 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1515. Min Act: -0.0004

Data Index: 636036 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1441. Min Act: -0.0004

Data Index: 850202 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1271. Min Act: -0.0004

Data Index: 1538639 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1354. Min Act: -0.0004

Data Index: 946791 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1198. Min Act: -0.0004

Data Index: 231734 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1177. Min Act: -0.0004

Data Index: 139429 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1225. Min Act: -0.0004

Data Index: 1059384 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1088. Min Act: -0.0004

Data Index: 603316 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1092. Min Act: -0.0004

Data Index: 611807 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1068. Min Act: -0.0004

Data Index: 296977 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1046. Min Act: -0.0004

Data Index: 570777 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1081. Min Act: -0.0004

Data Index: 991984 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1021. Min Act: -0.0004

Data Index: 609540 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1068. Min Act: -0.0004

Data Index: 482769 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0972. Min Act: -0.0004

Data Index: 449702 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0973. Min Act: -0.0004

Data Index: 116084 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0970. Min Act: -0.0004

Data Index: 777715 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0968. Min Act: -0.0004

Data Index: 1196388 (C4 (Web Text))

Max Activating Token Index: 1023