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

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

Neuron 535 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0752. Min Act: -0.0000

Data Index: 130588 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1249815 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0541. Min Act: -0.0001

Data Index: 584814 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0540. Min Act: -0.0000

Data Index: 911037 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0538. Min Act: -0.0000

Data Index: 604351 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0508. Min Act: -0.0001

Data Index: 566880 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1055295 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0456. Min Act: -0.0001

Data Index: 946714 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0473. Min Act: -0.0001

Data Index: 51459 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0448. Min Act: -0.0001

Data Index: 219244 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0441. Min Act: -0.0001

Data Index: 345085 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0477. Min Act: -0.0000

Data Index: 1156759 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0457. Min Act: -0.0001

Data Index: 281054 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0421. Min Act: -0.0001

Data Index: 266743 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0450. Min Act: -0.0000

Data Index: 508946 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0401. Min Act: -0.0001

Data Index: 465991 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0408. Min Act: -0.0000

Data Index: 1337275 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0424. Min Act: -0.0001

Data Index: 6600 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0422. Min Act: -0.0000

Data Index: 670772 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0421. Min Act: -0.0000

Data Index: 759675 (C4 (Web Text))

Max Activating Token Index: 583