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

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

Neuron 4565 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2315. Min Range: -1.2315

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1152569 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 1.2315. Min Range: -1.2315

Max Act: 1.0685. Min Act: -0.0000

Data Index: 1198403 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 1.2315. Min Range: -1.2315

Max Act: 1.0865. Min Act: -0.0000

Data Index: 344965 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8703. Min Act: -0.0000

Data Index: 543880 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9076. Min Act: -0.0000

Data Index: 739393 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8877. Min Act: -0.0000

Data Index: 815759 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1222505 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1278471 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9162. Min Act: -0.0000

Data Index: 793237 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8774. Min Act: -0.0000

Data Index: 210537 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9153. Min Act: -0.0000

Data Index: 746705 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8672. Min Act: -0.0000

Data Index: 1237840 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8440. Min Act: -0.0000

Data Index: 179569 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8652. Min Act: -0.0000

Data Index: 118238 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1341175 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1123069 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8027. Min Act: -0.0000

Data Index: 815627 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8998. Min Act: -0.0000

Data Index: 904319 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8255. Min Act: -0.0000

Data Index: 1255836 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1139708 (C4 (Web Text))

Max Activating Token Index: 472