Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4267 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.4975. Min Act: -0.0001

Data Index: 436098 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.4850. Min Act: -0.0001

Data Index: 853046 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3787. Min Act: -0.0001

Data Index: 941348 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3409. Min Act: -0.0001

Data Index: 454411 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3668. Min Act: -0.0001

Data Index: 1165494 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3942. Min Act: -0.0001

Data Index: 23874 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3173. Min Act: -0.0001

Data Index: 865400 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3281. Min Act: -0.0001

Data Index: 419883 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3230. Min Act: -0.0001

Data Index: 1210295 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3104. Min Act: -0.0001

Data Index: 676396 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.2975. Min Act: -0.0001

Data Index: 464889 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.2690. Min Act: -0.0001

Data Index: 211615 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3036. Min Act: -0.0001

Data Index: 630621 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.2797. Min Act: -0.0001

Data Index: 1067972 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.2771. Min Act: -0.0001

Data Index: 837767 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.2946. Min Act: -0.0001

Data Index: 1353037 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.2665. Min Act: -0.0001

Data Index: 616829 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.2649. Min Act: -0.0001

Data Index: 480019 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.2771. Min Act: -0.0001

Data Index: 445464 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3188. Min Act: -0.0001

Data Index: 968247 (C4 (Web Text))

Max Activating Token Index: 302