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

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

Neuron 2322 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: 0.4523. Min Range: -0.4523

Max Act: 0.4523. Min Act: -0.0001

Data Index: 175986 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4227. Min Act: -0.0001

Data Index: 916158 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4415. Min Act: -0.0001

Data Index: 817130 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4225. Min Act: -0.0001

Data Index: 43742 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4045. Min Act: -0.0001

Data Index: 808423 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4259. Min Act: -0.0001

Data Index: 895895 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4168. Min Act: -0.0001

Data Index: 866132 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.3961. Min Act: -0.0001

Data Index: 302478 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4107. Min Act: -0.0001

Data Index: 639317 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.3975. Min Act: -0.0001

Data Index: 388749 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.3838. Min Act: -0.0001

Data Index: 593464 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.4078. Min Act: -0.0001

Data Index: 26662 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.3892. Min Act: -0.0001

Data Index: 1223250 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.3775. Min Act: -0.0001

Data Index: 165610 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.3981. Min Act: -0.0001

Data Index: 244549 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.3759. Min Act: -0.0001

Data Index: 716875 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.3873. Min Act: -0.0001

Data Index: 919279 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.3948. Min Act: -0.0001

Data Index: 311145 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.3648. Min Act: -0.0001

Data Index: 1350506 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.4523. Min Range: -0.4523

Max Act: 0.3858. Min Act: -0.0001

Data Index: 845019 (C4 (Web Text))

Max Activating Token Index: 588