Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1735 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3336. Min Act: -0.0003

Data Index: 33056 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3361. Min Act: -0.0003

Data Index: 791779 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3160. Min Act: -0.0003

Data Index: 128073 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3014. Min Act: -0.0003

Data Index: 1009755 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2868. Min Act: -0.0003

Data Index: 607557 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2878. Min Act: -0.0003

Data Index: 397232 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2774. Min Act: -0.0003

Data Index: 1116686 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2850. Min Act: -0.0003

Data Index: 446759 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2871. Min Act: -0.0003

Data Index: 165658 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2783. Min Act: -0.0003

Data Index: 769487 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2778. Min Act: -0.0003

Data Index: 167030 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2827. Min Act: -0.0003

Data Index: 1282167 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2747. Min Act: -0.0003

Data Index: 200319 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2779. Min Act: -0.0003

Data Index: 737266 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2952. Min Act: -0.0003

Data Index: 906287 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2826. Min Act: -0.0003

Data Index: 115402 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2706. Min Act: -0.0003

Data Index: 1098978 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2752. Min Act: -0.0003

Data Index: 513251 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2410. Min Act: -0.0003

Data Index: 1022661 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2681. Min Act: -0.0003

Data Index: 924670 (C4 (Web Text))

Max Activating Token Index: 94