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

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

Neuron 4970 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.5008. Min Act: -0.0002

Data Index: 1204265 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.3026. Min Act: -0.0002

Data Index: 419600 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1299. Min Act: -0.0002

Data Index: 184878 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1160. Min Act: -0.0002

Data Index: 10092 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1185. Min Act: -0.0002

Data Index: 193855 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.0334. Min Act: -0.0002

Data Index: 988917 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.0470. Min Act: -0.0002

Data Index: 512464 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 2.5008. Min Range: -2.5008

Max Act: 1.9202. Min Act: -0.0002

Data Index: 828840 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 2.5008. Min Range: -2.5008

Max Act: 1.8865. Min Act: -0.0002

Data Index: 1342191 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 2.5008. Min Range: -2.5008

Max Act: 1.9118. Min Act: -0.0002

Data Index: 1354143 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 2.5008. Min Range: -2.5008

Max Act: 1.8879. Min Act: -0.0002

Data Index: 704272 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 2.5008. Min Range: -2.5008

Max Act: 1.9387. Min Act: -0.0002

Data Index: 1177426 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 2.5008. Min Range: -2.5008

Max Act: 1.9393. Min Act: -0.0002

Data Index: 875633 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 2.5008. Min Range: -2.5008

Max Act: 1.8621. Min Act: -0.0002

Data Index: 1254087 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 2.5008. Min Range: -2.5008

Max Act: 1.8419. Min Act: -0.0002

Data Index: 1358209 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 2.5008. Min Range: -2.5008

Max Act: 1.8676. Min Act: -0.0002

Data Index: 1257553 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 2.5008. Min Range: -2.5008

Max Act: 1.7742. Min Act: -0.0002

Data Index: 924860 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 2.5008. Min Range: -2.5008

Max Act: 1.7957. Min Act: -0.0002

Data Index: 869892 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 2.5008. Min Range: -2.5008

Max Act: 1.8120. Min Act: -0.0002

Data Index: 1018048 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 2.5008. Min Range: -2.5008

Max Act: 1.7692. Min Act: -0.0002

Data Index: 756112 (C4 (Web Text))

Max Activating Token Index: 947