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

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

Neuron 2871 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: 0.9402. Min Range: -0.9402

Max Act: 0.9402. Min Act: -0.0000

Data Index: 485668 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9229. Min Act: -0.0001

Data Index: 1298164 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1022479 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1250701 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7968. Min Act: -0.0000

Data Index: 1110227 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7388. Min Act: -0.0000

Data Index: 631716 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7333. Min Act: -0.0001

Data Index: 1563307 (Python Code)

Max Activating Token Index: 984

Text #7

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7100. Min Act: -0.0000

Data Index: 117143 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7652. Min Act: -0.0000

Data Index: 14998 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1551853 (Python Code)

Max Activating Token Index: 381

Text #10

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7055. Min Act: -0.0000

Data Index: 675806 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7039. Min Act: -0.0001

Data Index: 1425665 (Python Code)

Max Activating Token Index: 750

Text #12

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6915. Min Act: -0.0000

Data Index: 505609 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6605. Min Act: -0.0000

Data Index: 95778 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1358717 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6689. Min Act: -0.0000

Data Index: 408739 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1098582 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1023183 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6592. Min Act: -0.0000

Data Index: 841920 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6746. Min Act: -0.0000

Data Index: 730091 (C4 (Web Text))

Max Activating Token Index: 527