Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2425 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.5218. Min Act: -0.0001

Data Index: 992568 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4478. Min Act: -0.0001

Data Index: 829232 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4097. Min Act: -0.0001

Data Index: 1308901 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3493. Min Act: -0.0001

Data Index: 763887 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3788. Min Act: -0.0001

Data Index: 196509 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3793. Min Act: -0.0001

Data Index: 206816 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3873. Min Act: -0.0001

Data Index: 864254 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3751. Min Act: -0.0001

Data Index: 1271728 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3991. Min Act: -0.0001

Data Index: 247371 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4010. Min Act: -0.0001

Data Index: 461706 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3674. Min Act: -0.0001

Data Index: 465654 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3851. Min Act: -0.0001

Data Index: 1105485 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3673. Min Act: -0.0001

Data Index: 308319 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3476. Min Act: -0.0001

Data Index: 849782 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3552. Min Act: -0.0001

Data Index: 963692 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3566. Min Act: -0.0001

Data Index: 611100 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3690. Min Act: -0.0001

Data Index: 708961 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3646. Min Act: -0.0001

Data Index: 70267 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3626. Min Act: -0.0001

Data Index: 660604 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3407. Min Act: -0.0001

Data Index: 326353 (C4 (Web Text))

Max Activating Token Index: 277