Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3115 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1919. Min Range: -2.1919

Max Act: 2.1919. Min Act: -0.0000

Data Index: 191306 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.9211. Min Act: -0.0000

Data Index: 1283922 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.9983. Min Act: -0.0000

Data Index: 69999 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.7505. Min Act: -0.0000

Data Index: 1049854 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.7278. Min Act: -0.0000

Data Index: 731158 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.5624. Min Act: -0.0000

Data Index: 1204642 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.4533. Min Act: -0.0000

Data Index: 225344 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.4362. Min Act: -0.0000

Data Index: 1173048 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.1483. Min Act: -0.0000

Data Index: 1145849 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.1920. Min Act: -0.0000

Data Index: 1089862 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.1787. Min Act: -0.0000

Data Index: 1127363 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.2117. Min Act: -0.0000

Data Index: 867910 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.1381. Min Act: -0.0000

Data Index: 790576 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.2009. Min Act: -0.0000

Data Index: 44409 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.2088. Min Act: -0.0000

Data Index: 1216437 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.2140. Min Act: -0.0000

Data Index: 636110 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.1981. Min Act: -0.0000

Data Index: 679667 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.0651. Min Act: -0.0000

Data Index: 922734 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.1894. Min Act: -0.0000

Data Index: 156044 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 2.1919. Min Range: -2.1919

Max Act: 1.0957. Min Act: -0.0000

Data Index: 1479045 (Python Code)

Max Activating Token Index: 42