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

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

Neuron 1811 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: 0.1198. Min Range: -0.1198

Max Act: 0.1174. Min Act: -0.0002

Data Index: 474619 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1198. Min Act: -0.0001

Data Index: 143968 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1045. Min Act: -0.0002

Data Index: 556877 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1119. Min Act: -0.0002

Data Index: 811319 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1136. Min Act: -0.0002

Data Index: 811194 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1034. Min Act: -0.0002

Data Index: 922862 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1005. Min Act: -0.0002

Data Index: 649183 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0981. Min Act: -0.0002

Data Index: 175730 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0961. Min Act: -0.0002

Data Index: 923517 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0973. Min Act: -0.0002

Data Index: 400787 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0970. Min Act: -0.0002

Data Index: 457673 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0953. Min Act: -0.0002

Data Index: 187000 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0906. Min Act: -0.0002

Data Index: 693676 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0891. Min Act: -0.0002

Data Index: 667222 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0890. Min Act: -0.0002

Data Index: 757771 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1021367 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0867. Min Act: -0.0002

Data Index: 105303 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0885. Min Act: -0.0002

Data Index: 69396 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0920. Min Act: -0.0002

Data Index: 699765 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0922. Min Act: -0.0002

Data Index: 276761 (C4 (Web Text))

Max Activating Token Index: 634