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

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

Neuron 3795 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.6698. Min Act: -0.0000

Data Index: 1351800 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.4703. Min Act: -0.0000

Data Index: 293531 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.4750. Min Act: -0.0000

Data Index: 932841 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.3513. Min Act: -0.0000

Data Index: 366538 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.4760. Min Act: -0.0000

Data Index: 542627 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.3328. Min Act: -0.0000

Data Index: 404573 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.1515. Min Act: -0.0000

Data Index: 40157 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.3224. Min Act: -0.0000

Data Index: 1052040 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.3950. Min Act: -0.0000

Data Index: 382205 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.1943. Min Act: -0.0000

Data Index: 881543 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.3406. Min Act: -0.0000

Data Index: 627421 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.2056. Min Act: -0.0000

Data Index: 263135 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.2403. Min Act: -0.0000

Data Index: 744141 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.2689. Min Act: -0.0000

Data Index: 382156 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.1380. Min Act: -0.0000

Data Index: 581411 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.1352. Min Act: -0.0000

Data Index: 538006 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.2211. Min Act: -0.0000

Data Index: 539398 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.0384. Min Act: -0.0000

Data Index: 797923 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1074072 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 1.6698. Min Range: -1.6698

Max Act: 1.1327. Min Act: -0.0000

Data Index: 580298 (C4 (Web Text))

Max Activating Token Index: 777