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

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

Neuron 717 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: 0.5543. Min Range: -0.5543

Max Act: 0.5543. Min Act: -0.0001

Data Index: 316774 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4891. Min Act: -0.0002

Data Index: 128713 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5296. Min Act: -0.0002

Data Index: 1189912 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5169. Min Act: -0.0001

Data Index: 25072 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5057. Min Act: -0.0002

Data Index: 693897 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5018. Min Act: -0.0001

Data Index: 570453 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5089. Min Act: -0.0001

Data Index: 592221 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5090. Min Act: -0.0002

Data Index: 1331771 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5002. Min Act: -0.0002

Data Index: 1285157 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4778. Min Act: -0.0002

Data Index: 1218139 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4891. Min Act: -0.0002

Data Index: 29135 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5001. Min Act: -0.0002

Data Index: 976446 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4835. Min Act: -0.0001

Data Index: 740964 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5108. Min Act: -0.0002

Data Index: 168801 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4943. Min Act: -0.0002

Data Index: 355300 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4738. Min Act: -0.0002

Data Index: 242762 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4882. Min Act: -0.0002

Data Index: 542821 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4699. Min Act: -0.0002

Data Index: 282657 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4525. Min Act: -0.0002

Data Index: 175704 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4630. Min Act: -0.0002

Data Index: 307814 (C4 (Web Text))

Max Activating Token Index: 137