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

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

Neuron 698 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3954. Min Range: -3.3954

Max Act: 3.3749. Min Act: -0.0000

Data Index: 506280 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 3.3954. Min Range: -3.3954

Max Act: 3.3954. Min Act: -0.0000

Data Index: 1194371 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 3.3954. Min Range: -3.3954

Max Act: 3.2591. Min Act: -0.0000

Data Index: 595780 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 3.3954. Min Range: -3.3954

Max Act: 3.3871. Min Act: -0.0000

Data Index: 961031 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 3.3954. Min Range: -3.3954

Max Act: 2.9950. Min Act: -0.0000

Data Index: 411771 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 3.3954. Min Range: -3.3954

Max Act: 3.0701. Min Act: -0.0000

Data Index: 770757 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 3.3954. Min Range: -3.3954

Max Act: 3.2206. Min Act: -0.0000

Data Index: 393801 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 3.3954. Min Range: -3.3954

Max Act: 3.1630. Min Act: -0.0000

Data Index: 166003 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 3.3954. Min Range: -3.3954

Max Act: 3.1422. Min Act: -0.0000

Data Index: 350170 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 3.3954. Min Range: -3.3954

Max Act: 2.9139. Min Act: -0.0000

Data Index: 844728 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 3.3954. Min Range: -3.3954

Max Act: 2.8497. Min Act: -0.0000

Data Index: 1027722 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 3.3954. Min Range: -3.3954

Max Act: 2.6929. Min Act: -0.0000

Data Index: 655677 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 3.3954. Min Range: -3.3954

Max Act: 2.7886. Min Act: -0.0000

Data Index: 1333283 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 3.3954. Min Range: -3.3954

Max Act: 3.0737. Min Act: -0.0000

Data Index: 589688 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 3.3954. Min Range: -3.3954

Max Act: 2.9796. Min Act: -0.0000

Data Index: 1169523 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 3.3954. Min Range: -3.3954

Max Act: 2.7621. Min Act: -0.0000

Data Index: 494511 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 3.3954. Min Range: -3.3954

Max Act: 2.8949. Min Act: 0.0000

Data Index: 1185048 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 3.3954. Min Range: -3.3954

Max Act: 2.8719. Min Act: -0.0000

Data Index: 6543 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 3.3954. Min Range: -3.3954

Max Act: 2.7238. Min Act: -0.0000

Data Index: 1283550 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 3.3954. Min Range: -3.3954

Max Act: 2.8703. Min Act: -0.0000

Data Index: 741305 (C4 (Web Text))

Max Activating Token Index: 128