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

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

Neuron 3272 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0213. Min Range: -1.0213

Max Act: 1.0213. Min Act: -0.0000

Data Index: 739647 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.8647. Min Act: -0.0000

Data Index: 1299255 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.6653. Min Act: -0.0000

Data Index: 618812 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1539540 (Python Code)

Max Activating Token Index: 668

Text #4

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.6532. Min Act: -0.0000

Data Index: 330752 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.6468. Min Act: -0.0000

Data Index: 722910 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.6182. Min Act: -0.0000

Data Index: 675017 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1067561 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.6029. Min Act: -0.0000

Data Index: 797564 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.5752. Min Act: -0.0000

Data Index: 54683 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1080843 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1019565 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.5315. Min Act: -0.0000

Data Index: 842672 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.4825. Min Act: -0.0000

Data Index: 709842 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1428687 (Python Code)

Max Activating Token Index: 741

Text #15

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.5078. Min Act: -0.0000

Data Index: 640656 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.5203. Min Act: -0.0000

Data Index: 597069 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.5336. Min Act: -0.0000

Data Index: 923643 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.5003. Min Act: -0.0000

Data Index: 658663 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 1.0213. Min Range: -1.0213

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1076267 (C4 (Web Text))

Max Activating Token Index: 874