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

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

Neuron 3885 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.6706. Min Act: -0.0000

Data Index: 807702 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.2311. Min Act: -0.0000

Data Index: 1047784 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.2920. Min Act: -0.0000

Data Index: 1288567 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.1710. Min Act: -0.0000

Data Index: 1063960 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.1271. Min Act: -0.0000

Data Index: 774332 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.3411. Min Act: -0.0000

Data Index: 1374925 (Python Code)

Max Activating Token Index: 94

Text #6

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.0909. Min Act: -0.0000

Data Index: 94459 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.1762. Min Act: -0.0000

Data Index: 1481778 (Python Code)

Max Activating Token Index: 903

Text #8

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.2957. Min Act: -0.0000

Data Index: 943572 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.1121. Min Act: -0.0000

Data Index: 1351114 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 2.6706. Min Range: -2.6706

Max Act: 1.9725. Min Act: -0.0000

Data Index: 806214 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.2070. Min Act: -0.0000

Data Index: 1098169 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 2.6706. Min Range: -2.6706

Max Act: 1.9582. Min Act: -0.0000

Data Index: 149421 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.0486. Min Act: -0.0000

Data Index: 374532 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.1509. Min Act: -0.0000

Data Index: 1042268 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.1385. Min Act: -0.0000

Data Index: 1469044 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 2.6706. Min Range: -2.6706

Max Act: 1.7082. Min Act: -0.0000

Data Index: 1536907 (Python Code)

Max Activating Token Index: 601

Text #17

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.0922. Min Act: -0.0000

Data Index: 676056 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 2.6706. Min Range: -2.6706

Max Act: 2.0027. Min Act: -0.0000

Data Index: 407836 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 2.6706. Min Range: -2.6706

Max Act: 1.7787. Min Act: -0.0000

Data Index: 1526779 (Python Code)

Max Activating Token Index: 326