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

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

Neuron 232 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: 0.8172. Min Range: -0.8172

Max Act: 0.8172. Min Act: -0.0003

Data Index: 469070 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.7458. Min Act: -0.0002

Data Index: 1218562 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.7144. Min Act: -0.0002

Data Index: 1096537 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.7390. Min Act: -0.0002

Data Index: 298947 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.7291. Min Act: -0.0002

Data Index: 1335436 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6950. Min Act: -0.0002

Data Index: 250199 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6894. Min Act: -0.0002

Data Index: 846210 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6982. Min Act: -0.0002

Data Index: 378713 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6687. Min Act: -0.0002

Data Index: 400332 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6855. Min Act: -0.0002

Data Index: 993679 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6725. Min Act: -0.0002

Data Index: 1197845 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6838. Min Act: -0.0002

Data Index: 176303 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6678. Min Act: -0.0002

Data Index: 1298055 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6716. Min Act: -0.0002

Data Index: 762445 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6755. Min Act: -0.0002

Data Index: 300627 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6632. Min Act: -0.0002

Data Index: 285597 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6660. Min Act: -0.0002

Data Index: 664970 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6664. Min Act: -0.0002

Data Index: 735853 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6754. Min Act: -0.0002

Data Index: 12648 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6739. Min Act: -0.0003

Data Index: 1123449 (C4 (Web Text))

Max Activating Token Index: 777