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

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

Neuron 5812 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: 1.0601. Min Range: -1.0601

Max Act: 1.0601. Min Act: -0.0000

Data Index: 1322702 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.9621. Min Act: -0.0000

Data Index: 945034 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.9323. Min Act: -0.0000

Data Index: 304011 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.9410. Min Act: -0.0000

Data Index: 47975 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.9705. Min Act: 0.0000

Data Index: 399543 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.9133. Min Act: 0.0000

Data Index: 344492 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.9732. Min Act: -0.0000

Data Index: 795397 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1062297 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.8567. Min Act: -0.0000

Data Index: 678335 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1087395 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1072413 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.7401. Min Act: 0.0000

Data Index: 1301373 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.7302. Min Act: -0.0000

Data Index: 521188 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.7424. Min Act: -0.0000

Data Index: 560188 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.6797. Min Act: -0.0000

Data Index: 425337 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.6743. Min Act: -0.0000

Data Index: 184056 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.6990. Min Act: -0.0000

Data Index: 233087 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.6539. Min Act: 0.0000

Data Index: 694762 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.6570. Min Act: -0.0000

Data Index: 257210 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.6349. Min Act: -0.0000

Data Index: 998753 (C4 (Web Text))

Max Activating Token Index: 605