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

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

Neuron 3780 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2327. Min Range: -3.2327

Max Act: 3.1813. Min Act: -0.0000

Data Index: 285446 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 3.2327. Min Range: -3.2327

Max Act: 3.1268. Min Act: -0.0000

Data Index: 509242 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 3.2327. Min Range: -3.2327

Max Act: 3.2327. Min Act: -0.0000

Data Index: 719096 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.9327. Min Act: -0.0000

Data Index: 655392 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.8780. Min Act: -0.0000

Data Index: 752350 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 3.2327. Min Range: -3.2327

Max Act: 3.0514. Min Act: -0.0000

Data Index: 430494 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.8522. Min Act: -0.0000

Data Index: 841180 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.8467. Min Act: -0.0000

Data Index: 531263 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.8989. Min Act: -0.0000

Data Index: 266279 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.6244. Min Act: -0.0000

Data Index: 934886 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.5972. Min Act: -0.0000

Data Index: 1132680 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.5423. Min Act: -0.0000

Data Index: 696289 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.7571. Min Act: -0.0000

Data Index: 569976 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.7416. Min Act: -0.0000

Data Index: 604218 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.6190. Min Act: -0.0000

Data Index: 656009 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.5115. Min Act: -0.0000

Data Index: 1103431 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.2853. Min Act: -0.0000

Data Index: 394981 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.4695. Min Act: -0.0000

Data Index: 77997 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.6186. Min Act: -0.0000

Data Index: 1147807 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 3.2327. Min Range: -3.2327

Max Act: 2.4568. Min Act: -0.0000

Data Index: 475969 (C4 (Web Text))

Max Activating Token Index: 942