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

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

Neuron 2467 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5423. Min Act: -0.0000

Data Index: 31639 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4402. Min Act: -0.0000

Data Index: 578628 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1179328 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4385. Min Act: -0.0000

Data Index: 705711 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4443. Min Act: -0.0000

Data Index: 436400 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4271. Min Act: -0.0000

Data Index: 788003 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3960. Min Act: -0.0000

Data Index: 646001 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3680. Min Act: -0.0000

Data Index: 809671 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3760. Min Act: -0.0000

Data Index: 584778 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1152409 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3609. Min Act: -0.0000

Data Index: 774518 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3625. Min Act: -0.0000

Data Index: 171913 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3754. Min Act: -0.0000

Data Index: 757747 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1040594 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3736. Min Act: -0.0000

Data Index: 663359 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3934. Min Act: -0.0000

Data Index: 475458 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3418. Min Act: -0.0000

Data Index: 949080 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1181445 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3632. Min Act: -0.0000

Data Index: 251920 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1023157 (C4 (Web Text))

Max Activating Token Index: 216