Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1215 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.8453. Min Act: -0.0001

Data Index: 950978 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.6777. Min Act: -0.0001

Data Index: 395169 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.7552. Min Act: -0.0001

Data Index: 882311 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.6540. Min Act: -0.0001

Data Index: 171656 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.4166. Min Act: -0.0001

Data Index: 1296600 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.3811. Min Act: -0.0001

Data Index: 976375 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.3949. Min Act: -0.0001

Data Index: 1061424 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.3496. Min Act: -0.0001

Data Index: 428416 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.2725. Min Act: -0.0001

Data Index: 1152267 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.2681. Min Act: -0.0001

Data Index: 356351 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.1953. Min Act: -0.0001

Data Index: 646406 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.2452. Min Act: -0.0001

Data Index: 890496 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.1672. Min Act: -0.0001

Data Index: 326243 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.2363. Min Act: -0.0001

Data Index: 109458 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.2783. Min Act: -0.0001

Data Index: 67272 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.2670. Min Act: -0.0001

Data Index: 888193 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.2688. Min Act: -0.0001

Data Index: 889975 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.1744. Min Act: -0.0001

Data Index: 287681 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.1667. Min Act: -0.0001

Data Index: 853942 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.1011. Min Act: -0.0001

Data Index: 1034875 (C4 (Web Text))

Max Activating Token Index: 419