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

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

Neuron 5269 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.6276. Min Act: -0.0002

Data Index: 437681 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.2042. Min Act: -0.0002

Data Index: 136092 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.0688. Min Act: -0.0002

Data Index: 728139 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.0570. Min Act: -0.0002

Data Index: 596965 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.0332. Min Act: -0.0002

Data Index: 1611193 (Python Code)

Max Activating Token Index: 297

Text #5

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.0617. Min Act: -0.0002

Data Index: 492512 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.0713. Min Act: -0.0002

Data Index: 603635 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.0398. Min Act: -0.0002

Data Index: 351289 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 1.6276. Min Range: -1.6276

Max Act: 0.9653. Min Act: -0.0002

Data Index: 86329 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 1.6276. Min Range: -1.6276

Max Act: 0.9844. Min Act: -0.0002

Data Index: 1310990 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 1.6276. Min Range: -1.6276

Max Act: 0.9757. Min Act: -0.0002

Data Index: 1564667 (Python Code)

Max Activating Token Index: 731

Text #11

Max Range: 1.6276. Min Range: -1.6276

Max Act: 0.9759. Min Act: -0.0002

Data Index: 94295 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 1.6276. Min Range: -1.6276

Max Act: 0.9375. Min Act: -0.0002

Data Index: 1072807 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 1.6276. Min Range: -1.6276

Max Act: 0.9308. Min Act: -0.0002

Data Index: 956119 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 1.6276. Min Range: -1.6276

Max Act: 0.8819. Min Act: -0.0002

Data Index: 994989 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 1.6276. Min Range: -1.6276

Max Act: 0.9124. Min Act: -0.0002

Data Index: 146352 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 1.6276. Min Range: -1.6276

Max Act: 0.9640. Min Act: -0.0002

Data Index: 1457118 (Python Code)

Max Activating Token Index: 536

Text #17

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.0902. Min Act: -0.0002

Data Index: 832543 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 1.6276. Min Range: -1.6276

Max Act: 0.9418. Min Act: -0.0002

Data Index: 1632158 (Python Code)

Max Activating Token Index: 508

Text #19

Max Range: 1.6276. Min Range: -1.6276

Max Act: 0.9065. Min Act: -0.0002

Data Index: 1233294 (C4 (Web Text))

Max Activating Token Index: 914