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

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

Neuron 399 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.6463. Min Act: -0.0000

Data Index: 557101 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.3230. Min Act: -0.0000

Data Index: 1359152 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.2385. Min Act: -0.0000

Data Index: 179141 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.1015. Min Act: -0.0000

Data Index: 1610513 (Python Code)

Max Activating Token Index: 153

Text #4

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.1913. Min Act: -0.0000

Data Index: 1634994 (Python Code)

Max Activating Token Index: 468

Text #5

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.1675. Min Act: -0.0001

Data Index: 590778 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.1084. Min Act: -0.0000

Data Index: 291699 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.1064. Min Act: -0.0000

Data Index: 1417576 (Python Code)

Max Activating Token Index: 307

Text #8

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1487801 (Python Code)

Max Activating Token Index: 65

Text #9

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1410744 (Python Code)

Max Activating Token Index: 416

Text #10

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.1025. Min Act: -0.0001

Data Index: 911750 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.0761. Min Act: -0.0000

Data Index: 1643406 (Python Code)

Max Activating Token Index: 506

Text #12

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.1075. Min Act: -0.0000

Data Index: 1576325 (Python Code)

Max Activating Token Index: 217

Text #13

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.1103. Min Act: -0.0001

Data Index: 458376 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.6463. Min Range: -1.6463

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1585188 (Python Code)

Max Activating Token Index: 993

Text #15

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1413000 (Python Code)

Max Activating Token Index: 613

Text #16

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.0199. Min Act: -0.0000

Data Index: 1524631 (Python Code)

Max Activating Token Index: 400

Text #17

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1526360 (Python Code)

Max Activating Token Index: 526

Text #18

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.0982. Min Act: -0.0000

Data Index: 1647888 (Python Code)

Max Activating Token Index: 251

Text #19

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1500708 (Python Code)

Max Activating Token Index: 984