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

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

Neuron 2669 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: 1.1989. Min Range: -1.1989

Max Act: 1.1989. Min Act: -0.0001

Data Index: 354954 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 1.1989. Min Range: -1.1989

Max Act: 1.0781. Min Act: -0.0001

Data Index: 246385 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 1.1989. Min Range: -1.1989

Max Act: 1.0604. Min Act: -0.0001

Data Index: 532461 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 1.1989. Min Range: -1.1989

Max Act: 1.1063. Min Act: -0.0001

Data Index: 1317600 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 1.1989. Min Range: -1.1989

Max Act: 1.0333. Min Act: -0.0001

Data Index: 199113 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.9570. Min Act: -0.0001

Data Index: 785091 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.9454. Min Act: -0.0001

Data Index: 290352 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.8626. Min Act: -0.0001

Data Index: 194392 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.8454. Min Act: -0.0001

Data Index: 279613 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.8752. Min Act: -0.0001

Data Index: 665926 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.9886. Min Act: -0.0001

Data Index: 544441 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.9694. Min Act: -0.0001

Data Index: 526730 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.9137. Min Act: -0.0001

Data Index: 661515 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.8100. Min Act: -0.0001

Data Index: 940105 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.8401. Min Act: -0.0001

Data Index: 1460670 (Python Code)

Max Activating Token Index: 813

Text #15

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.9277. Min Act: -0.0001

Data Index: 274661 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.8454. Min Act: -0.0001

Data Index: 562189 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.8922. Min Act: -0.0001

Data Index: 77 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.8512. Min Act: -0.0001

Data Index: 1337337 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 1.1989. Min Range: -1.1989

Max Act: 0.8524. Min Act: -0.0001

Data Index: 355701 (C4 (Web Text))

Max Activating Token Index: 557