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

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

Neuron 458 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4402. Min Range: -4.4402

Max Act: 4.4402. Min Act: -0.0000

Data Index: 610731 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 4.4402. Min Range: -4.4402

Max Act: 3.9667. Min Act: -0.0000

Data Index: 1120038 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 4.4402. Min Range: -4.4402

Max Act: 3.9147. Min Act: -0.0000

Data Index: 1332608 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 4.4402. Min Range: -4.4402

Max Act: 3.3367. Min Act: -0.0001

Data Index: 839448 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 4.4402. Min Range: -4.4402

Max Act: 3.2643. Min Act: -0.0000

Data Index: 611025 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 4.4402. Min Range: -4.4402

Max Act: 3.4055. Min Act: -0.0000

Data Index: 138592 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 4.4402. Min Range: -4.4402

Max Act: 3.1667. Min Act: -0.0000

Data Index: 622540 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 4.4402. Min Range: -4.4402

Max Act: 3.2112. Min Act: -0.0001

Data Index: 18448 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 4.4402. Min Range: -4.4402

Max Act: 3.0363. Min Act: -0.0001

Data Index: 892853 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 4.4402. Min Range: -4.4402

Max Act: 3.1235. Min Act: -0.0001

Data Index: 818971 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 4.4402. Min Range: -4.4402

Max Act: 2.9929. Min Act: -0.0000

Data Index: 120041 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 4.4402. Min Range: -4.4402

Max Act: 3.2467. Min Act: -0.0000

Data Index: 703642 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 4.4402. Min Range: -4.4402

Max Act: 2.9455. Min Act: -0.0000

Data Index: 307285 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 4.4402. Min Range: -4.4402

Max Act: 2.7866. Min Act: -0.0000

Data Index: 254673 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 4.4402. Min Range: -4.4402

Max Act: 3.0701. Min Act: -0.0001

Data Index: 936435 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 4.4402. Min Range: -4.4402

Max Act: 2.8939. Min Act: -0.0001

Data Index: 571764 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 4.4402. Min Range: -4.4402

Max Act: 2.8701. Min Act: -0.0000

Data Index: 165254 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 4.4402. Min Range: -4.4402

Max Act: 2.8251. Min Act: -0.0000

Data Index: 497519 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 4.4402. Min Range: -4.4402

Max Act: 2.9652. Min Act: -0.0000

Data Index: 1073088 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 4.4402. Min Range: -4.4402

Max Act: 3.1029. Min Act: -0.0000

Data Index: 236975 (C4 (Web Text))

Max Activating Token Index: 288