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

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

Neuron 3037 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.4053. Min Act: -0.0000

Data Index: 410911 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1813. Min Act: -0.0000

Data Index: 432942 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1459. Min Act: -0.0000

Data Index: 1231018 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.2046. Min Act: 0.0000

Data Index: 1471485 (Python Code)

Max Activating Token Index: 954

Text #4

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1196. Min Act: 0.0000

Data Index: 1611641 (Python Code)

Max Activating Token Index: 274

Text #5

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1538790 (Python Code)

Max Activating Token Index: 63

Text #6

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1415. Min Act: -0.0000

Data Index: 623584 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1524616 (Python Code)

Max Activating Token Index: 679

Text #8

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1524175 (Python Code)

Max Activating Token Index: 752

Text #9

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1310. Min Act: -0.0000

Data Index: 545277 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1116. Min Act: -0.0000

Data Index: 158333 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.0880. Min Act: -0.0000

Data Index: 1531007 (Python Code)

Max Activating Token Index: 766

Text #12

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.0890. Min Act: 0.0000

Data Index: 1180464 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.0950. Min Act: -0.0000

Data Index: 268488 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.0847. Min Act: -0.0000

Data Index: 1435922 (Python Code)

Max Activating Token Index: 745

Text #15

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1411. Min Act: -0.0000

Data Index: 717569 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1470. Min Act: 0.0000

Data Index: 1619733 (Python Code)

Max Activating Token Index: 931

Text #17

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1411. Min Act: 0.0000

Data Index: 1098161 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.0083. Min Act: -0.0000

Data Index: 578152 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.0695. Min Act: -0.0000

Data Index: 748821 (C4 (Web Text))

Max Activating Token Index: 194