Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4794 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1124377 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.6449. Min Act: -0.0000

Data Index: 656376 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5512. Min Act: -0.0000

Data Index: 860178 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5147. Min Act: -0.0000

Data Index: 809367 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5057. Min Act: -0.0000

Data Index: 477092 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5206. Min Act: -0.0000

Data Index: 76757 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4967. Min Act: -0.0000

Data Index: 572006 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4742. Min Act: -0.0000

Data Index: 999379 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4857. Min Act: -0.0000

Data Index: 310490 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4664. Min Act: -0.0000

Data Index: 674785 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1217914 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4662. Min Act: -0.0000

Data Index: 823909 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4630. Min Act: -0.0000

Data Index: 320528 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4336. Min Act: -0.0000

Data Index: 573050 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4457. Min Act: -0.0000

Data Index: 782001 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4574. Min Act: -0.0000

Data Index: 387063 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4393. Min Act: -0.0000

Data Index: 319502 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4559. Min Act: -0.0000

Data Index: 265494 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1179053 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4506. Min Act: -0.0000

Data Index: 584412 (C4 (Web Text))

Max Activating Token Index: 976