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

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

Neuron 2304 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.9230. Min Act: -0.0000

Data Index: 522953 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1312792 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1563572 (Python Code)

Max Activating Token Index: 775

Text #3

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5669. Min Act: -0.0000

Data Index: 225348 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1035345 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5647. Min Act: -0.0000

Data Index: 619687 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1321107 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1204156 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5568. Min Act: -0.0000

Data Index: 315597 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5234. Min Act: -0.0000

Data Index: 556766 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1395367 (Python Code)

Max Activating Token Index: 635

Text #11

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5146. Min Act: -0.0000

Data Index: 583784 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5287. Min Act: -0.0000

Data Index: 552446 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5188. Min Act: -0.0000

Data Index: 371778 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1385657 (Python Code)

Max Activating Token Index: 258

Text #15

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.4780. Min Act: -0.0000

Data Index: 770604 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5058. Min Act: -0.0000

Data Index: 767240 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5173. Min Act: -0.0000

Data Index: 948871 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.5332. Min Act: -0.0000

Data Index: 692462 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1456122 (Python Code)

Max Activating Token Index: 55