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

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

Neuron 5484 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.8866. Min Act: -0.0001

Data Index: 427245 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.3539. Min Act: -0.0001

Data Index: 932997 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.5007. Min Act: -0.0001

Data Index: 878655 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.4902. Min Act: -0.0001

Data Index: 1255011 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.4715. Min Act: -0.0001

Data Index: 355712 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.5815. Min Act: -0.0001

Data Index: 749512 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.2358. Min Act: -0.0001

Data Index: 891980 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.3246. Min Act: -0.0001

Data Index: 1161393 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.0906. Min Act: -0.0001

Data Index: 18843 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.1138. Min Act: -0.0001

Data Index: 439429 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.0409. Min Act: -0.0001

Data Index: 618789 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 3.8866. Min Range: -3.8866

Max Act: 2.9575. Min Act: -0.0001

Data Index: 204782 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 3.8866. Min Range: -3.8866

Max Act: 2.8195. Min Act: -0.0001

Data Index: 1130556 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 3.8866. Min Range: -3.8866

Max Act: 2.7081. Min Act: -0.0001

Data Index: 1197119 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 3.8866. Min Range: -3.8866

Max Act: 2.9485. Min Act: -0.0001

Data Index: 222527 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.0160. Min Act: -0.0001

Data Index: 1000764 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 3.8866. Min Range: -3.8866

Max Act: 2.8997. Min Act: -0.0001

Data Index: 98023 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.3355. Min Act: -0.0001

Data Index: 1187091 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.0457. Min Act: -0.0001

Data Index: 464137 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 3.8866. Min Range: -3.8866

Max Act: 2.8966. Min Act: -0.0001

Data Index: 961331 (C4 (Web Text))

Max Activating Token Index: 458