Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3317 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.8051. Min Act: -0.0001

Data Index: 1269821 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.7467. Min Act: -0.0001

Data Index: 787119 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.5841. Min Act: -0.0001

Data Index: 608708 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.5821. Min Act: -0.0001

Data Index: 251183 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.5177. Min Act: -0.0001

Data Index: 877861 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.6312. Min Act: -0.0001

Data Index: 57245 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.4069. Min Act: -0.0001

Data Index: 572038 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.4129. Min Act: -0.0001

Data Index: 442026 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.3082. Min Act: -0.0001

Data Index: 1235567 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.3220. Min Act: -0.0001

Data Index: 1648 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.3672. Min Act: -0.0001

Data Index: 951634 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.2327. Min Act: -0.0001

Data Index: 356963 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.3374. Min Act: -0.0001

Data Index: 325115 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.2363. Min Act: -0.0001

Data Index: 1134912 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.2623. Min Act: -0.0001

Data Index: 453670 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.3598. Min Act: -0.0001

Data Index: 1250414 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.2676. Min Act: -0.0001

Data Index: 321785 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.2856. Min Act: -0.0001

Data Index: 1002943 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.2495. Min Act: -0.0001

Data Index: 999833 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 1.8051. Min Range: -1.8051

Max Act: 1.2350. Min Act: -0.0001

Data Index: 1158976 (C4 (Web Text))

Max Activating Token Index: 538