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

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

Neuron 3062 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1214. Min Act: -0.0003

Data Index: 542227 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1067. Min Act: -0.0003

Data Index: 26574 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1177. Min Act: -0.0003

Data Index: 865945 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1130. Min Act: -0.0003

Data Index: 948756 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1066. Min Act: -0.0003

Data Index: 329892 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1053. Min Act: -0.0003

Data Index: 975957 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1085. Min Act: -0.0003

Data Index: 1198447 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1037. Min Act: -0.0003

Data Index: 241249 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0923. Min Act: -0.0003

Data Index: 551002 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1026. Min Act: -0.0003

Data Index: 383598 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1001. Min Act: -0.0003

Data Index: 933540 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0961. Min Act: -0.0003

Data Index: 36525 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0915. Min Act: -0.0003

Data Index: 1136016 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0740. Min Act: -0.0003

Data Index: 159095 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0950. Min Act: -0.0003

Data Index: 274 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0948. Min Act: -0.0003

Data Index: 966439 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0878. Min Act: -0.0003

Data Index: 1322005 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0892. Min Act: -0.0003

Data Index: 973951 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0907. Min Act: -0.0003

Data Index: 1049749 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0834. Min Act: -0.0003

Data Index: 382991 (C4 (Web Text))

Max Activating Token Index: 15