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

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

Neuron 1698 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: 4.0810. Min Range: -4.0810

Max Act: 4.0810. Min Act: -0.0000

Data Index: 431729 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.6516. Min Act: -0.0000

Data Index: 587454 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.6399. Min Act: -0.0000

Data Index: 1313024 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.3736. Min Act: -0.0000

Data Index: 645482 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.6512. Min Act: -0.0000

Data Index: 1023685 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.4928. Min Act: -0.0000

Data Index: 1339594 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.3301. Min Act: -0.0000

Data Index: 141174 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.2104. Min Act: -0.0000

Data Index: 998890 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.3721. Min Act: -0.0000

Data Index: 435864 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.1912. Min Act: -0.0000

Data Index: 312459 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.2567. Min Act: -0.0000

Data Index: 376327 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.1526. Min Act: -0.0000

Data Index: 770984 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.3125. Min Act: -0.0000

Data Index: 512962 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.2785. Min Act: -0.0000

Data Index: 395875 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.1309. Min Act: -0.0000

Data Index: 7297 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.4062. Min Act: -0.0000

Data Index: 1144525 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.0994. Min Act: -0.0000

Data Index: 72474 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.4021. Min Act: -0.0000

Data Index: 1196799 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.0953. Min Act: -0.0000

Data Index: 433740 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.2303. Min Act: -0.0000

Data Index: 63543 (C4 (Web Text))

Max Activating Token Index: 786