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

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

Neuron 3349 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.2698. Min Act: -0.0000

Data Index: 949279 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.2855. Min Act: -0.0000

Data Index: 338249 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.3008. Min Act: -0.0000

Data Index: 489061 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.0710. Min Act: -0.0000

Data Index: 1439423 (Python Code)

Max Activating Token Index: 244

Text #4

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1535738 (Python Code)

Max Activating Token Index: 648

Text #5

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1238698 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.0520. Min Act: -0.0000

Data Index: 1621189 (Python Code)

Max Activating Token Index: 342

Text #7

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8698. Min Act: -0.0000

Data Index: 847236 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.9643. Min Act: -0.0000

Data Index: 1392285 (Python Code)

Max Activating Token Index: 124

Text #9

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1431715 (Python Code)

Max Activating Token Index: 969

Text #10

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8979. Min Act: -0.0000

Data Index: 639996 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1375061 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1643380 (Python Code)

Max Activating Token Index: 361

Text #13

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8766. Min Act: -0.0000

Data Index: 1587503 (Python Code)

Max Activating Token Index: 632

Text #14

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.9337. Min Act: -0.0000

Data Index: 1534377 (Python Code)

Max Activating Token Index: 872

Text #15

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1469691 (Python Code)

Max Activating Token Index: 678

Text #16

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1446799 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8399. Min Act: -0.0000

Data Index: 1413436 (Python Code)

Max Activating Token Index: 304

Text #18

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8364. Min Act: -0.0000

Data Index: 1484264 (Python Code)

Max Activating Token Index: 141

Text #19

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1427631 (Python Code)

Max Activating Token Index: 54