Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1490 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1070. Min Act: -0.0002

Data Index: 568470 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0954. Min Act: -0.0002

Data Index: 898423 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0949. Min Act: -0.0002

Data Index: 235839 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0902. Min Act: -0.0001

Data Index: 482179 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0906. Min Act: -0.0001

Data Index: 940080 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1082608 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1104866 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0885. Min Act: -0.0001

Data Index: 184409 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0872. Min Act: -0.0001

Data Index: 733849 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0876. Min Act: -0.0002

Data Index: 103402 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0952. Min Act: -0.0002

Data Index: 37343 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1268409 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0847. Min Act: -0.0002

Data Index: 544030 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1066180 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0847. Min Act: -0.0002

Data Index: 162657 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0873. Min Act: -0.0001

Data Index: 624954 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1639360 (Python Code)

Max Activating Token Index: 419

Text #17

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0817. Min Act: -0.0002

Data Index: 256500 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0815. Min Act: -0.0002

Data Index: 977946 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0874. Min Act: -0.0001

Data Index: 305775 (C4 (Web Text))

Max Activating Token Index: 61