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

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

Neuron 227 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: 0.5711. Min Range: -0.5711

Max Act: 0.5711. Min Act: -0.0002

Data Index: 475049 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5497. Min Act: -0.0002

Data Index: 605720 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5703. Min Act: -0.0002

Data Index: 929790 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5417. Min Act: -0.0003

Data Index: 713399 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5101. Min Act: -0.0003

Data Index: 1164696 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5233. Min Act: -0.0002

Data Index: 1077222 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5167. Min Act: -0.0002

Data Index: 43052 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4975. Min Act: -0.0002

Data Index: 677283 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4789. Min Act: -0.0002

Data Index: 830837 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4773. Min Act: -0.0002

Data Index: 1213271 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4866. Min Act: -0.0003

Data Index: 175915 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4899. Min Act: -0.0002

Data Index: 1096156 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4710. Min Act: -0.0002

Data Index: 954207 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4711. Min Act: -0.0002

Data Index: 1204647 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4752. Min Act: -0.0002

Data Index: 521244 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4800. Min Act: -0.0002

Data Index: 424011 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4774. Min Act: -0.0002

Data Index: 621745 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4722. Min Act: -0.0002

Data Index: 576188 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4648. Min Act: -0.0002

Data Index: 654790 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4567. Min Act: -0.0002

Data Index: 1170492 (C4 (Web Text))

Max Activating Token Index: 61