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

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

Neuron 12 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7350. Min Range: -3.7350

Max Act: 3.7350. Min Act: -0.0000

Data Index: 85206 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 3.7350. Min Range: -3.7350

Max Act: 3.0293. Min Act: -0.0000

Data Index: 421677 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 3.7350. Min Range: -3.7350

Max Act: 3.1284. Min Act: -0.0000

Data Index: 834657 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 3.7350. Min Range: -3.7350

Max Act: 3.0307. Min Act: -0.0000

Data Index: 1296939 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.8087. Min Act: -0.0000

Data Index: 399508 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.9148. Min Act: -0.0000

Data Index: 955627 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.6946. Min Act: -0.0000

Data Index: 264425 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.9665. Min Act: -0.0000

Data Index: 28121 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.6061. Min Act: -0.0000

Data Index: 1352266 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.6311. Min Act: -0.0000

Data Index: 927282 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.5989. Min Act: -0.0000

Data Index: 561290 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.5690. Min Act: -0.0000

Data Index: 307888 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.5291. Min Act: -0.0000

Data Index: 787556 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.4088. Min Act: -0.0000

Data Index: 850421 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.5408. Min Act: -0.0000

Data Index: 827896 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.6558. Min Act: -0.0000

Data Index: 1021564 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.4600. Min Act: -0.0000

Data Index: 358998 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.4551. Min Act: -0.0000

Data Index: 671920 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.4284. Min Act: -0.0000

Data Index: 550054 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 3.7350. Min Range: -3.7350

Max Act: 2.2875. Min Act: -0.0000

Data Index: 20354 (C4 (Web Text))

Max Activating Token Index: 696