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

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

Neuron 121 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1068. Min Act: -0.0005

Data Index: 703229 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1068. Min Act: -0.0005

Data Index: 469777 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1049. Min Act: -0.0005

Data Index: 60117 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1059. Min Act: -0.0005

Data Index: 327268 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1007. Min Act: -0.0005

Data Index: 499916 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1004. Min Act: -0.0005

Data Index: 487195 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0976. Min Act: -0.0005

Data Index: 669971 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0969. Min Act: -0.0005

Data Index: 149524 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1010. Min Act: -0.0005

Data Index: 1284884 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0991. Min Act: -0.0005

Data Index: 316283 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0954. Min Act: -0.0005

Data Index: 1014421 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0993. Min Act: -0.0005

Data Index: 849365 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0959. Min Act: -0.0005

Data Index: 46440 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1010. Min Act: -0.0005

Data Index: 903166 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0953. Min Act: -0.0005

Data Index: 1134846 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0939. Min Act: -0.0005

Data Index: 831062 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0947. Min Act: -0.0005

Data Index: 993147 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0966. Min Act: -0.0005

Data Index: 183774 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0950. Min Act: -0.0005

Data Index: 254305 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0943. Min Act: -0.0005

Data Index: 791397 (C4 (Web Text))

Max Activating Token Index: 57