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

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

Neuron 5023 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: 1.5735. Min Range: -1.5735

Max Act: 1.5735. Min Act: -0.0002

Data Index: 998224 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.4803. Min Act: -0.0002

Data Index: 77253 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.5148. Min Act: -0.0002

Data Index: 529638 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.5011. Min Act: -0.0002

Data Index: 738470 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.4100. Min Act: -0.0002

Data Index: 862718 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.4206. Min Act: -0.0002

Data Index: 555910 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.4747. Min Act: -0.0002

Data Index: 1182439 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.4069. Min Act: -0.0002

Data Index: 971725 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.4133. Min Act: -0.0002

Data Index: 1121810 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.4024. Min Act: -0.0002

Data Index: 749398 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.3895. Min Act: -0.0002

Data Index: 181914 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.3952. Min Act: -0.0002

Data Index: 897806 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.3917. Min Act: -0.0002

Data Index: 971194 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.3655. Min Act: -0.0002

Data Index: 601260 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.3985. Min Act: -0.0002

Data Index: 280613 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.3667. Min Act: -0.0002

Data Index: 532740 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.3667. Min Act: -0.0002

Data Index: 928423 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.3816. Min Act: -0.0002

Data Index: 1355887 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.3549. Min Act: -0.0002

Data Index: 274274 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 1.5735. Min Range: -1.5735

Max Act: 1.3573. Min Act: -0.0002

Data Index: 709657 (C4 (Web Text))

Max Activating Token Index: 228