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

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

Neuron 5801 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: 5.3425. Min Range: -5.3425

Max Act: 5.3425. Min Act: -0.0000

Data Index: 120091 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 5.3425. Min Range: -5.3425

Max Act: 5.0062. Min Act: -0.0000

Data Index: 615844 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 5.3425. Min Range: -5.3425

Max Act: 4.3428. Min Act: -0.0000

Data Index: 617862 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 5.3425. Min Range: -5.3425

Max Act: 3.8095. Min Act: -0.0000

Data Index: 438935 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 5.3425. Min Range: -5.3425

Max Act: 3.8670. Min Act: -0.0000

Data Index: 214164 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 5.3425. Min Range: -5.3425

Max Act: 4.1622. Min Act: -0.0000

Data Index: 356340 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 5.3425. Min Range: -5.3425

Max Act: 3.4400. Min Act: -0.0000

Data Index: 1070395 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 5.3425. Min Range: -5.3425

Max Act: 3.6984. Min Act: -0.0000

Data Index: 123048 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 5.3425. Min Range: -5.3425

Max Act: 3.1721. Min Act: -0.0000

Data Index: 70256 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 5.3425. Min Range: -5.3425

Max Act: 3.2318. Min Act: -0.0000

Data Index: 661064 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 5.3425. Min Range: -5.3425

Max Act: 3.1438. Min Act: -0.0000

Data Index: 1109732 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 5.3425. Min Range: -5.3425

Max Act: 3.2449. Min Act: -0.0001

Data Index: 658215 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 5.3425. Min Range: -5.3425

Max Act: 3.1768. Min Act: -0.0000

Data Index: 290134 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 5.3425. Min Range: -5.3425

Max Act: 3.2702. Min Act: -0.0000

Data Index: 8620 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 5.3425. Min Range: -5.3425

Max Act: 2.8005. Min Act: -0.0000

Data Index: 256864 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 5.3425. Min Range: -5.3425

Max Act: 2.8335. Min Act: -0.0000

Data Index: 1025965 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 5.3425. Min Range: -5.3425

Max Act: 2.9164. Min Act: -0.0000

Data Index: 149643 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 5.3425. Min Range: -5.3425

Max Act: 3.3113. Min Act: -0.0000

Data Index: 925659 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 5.3425. Min Range: -5.3425

Max Act: 2.8058. Min Act: -0.0000

Data Index: 1227567 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 5.3425. Min Range: -5.3425

Max Act: 2.5251. Min Act: -0.0000

Data Index: 119062 (C4 (Web Text))

Max Activating Token Index: 212