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

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

Neuron 3577 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: 0.0722. Min Range: -0.0722

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1182472 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0572. Min Act: -0.0002

Data Index: 575948 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0522. Min Act: -0.0002

Data Index: 735024 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0513. Min Act: -0.0002

Data Index: 686506 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0523. Min Act: -0.0002

Data Index: 449543 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0499. Min Act: -0.0002

Data Index: 778349 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0487. Min Act: -0.0002

Data Index: 324153 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0470. Min Act: -0.0002

Data Index: 734963 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0474. Min Act: -0.0002

Data Index: 618140 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1323115 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1270900 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1346014 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0461. Min Act: -0.0002

Data Index: 65857 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0459. Min Act: -0.0002

Data Index: 284300 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1323693 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0437. Min Act: -0.0003

Data Index: 834124 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1085374 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0444. Min Act: -0.0002

Data Index: 334158 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0438. Min Act: -0.0002

Data Index: 614437 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1171838 (C4 (Web Text))

Max Activating Token Index: 317