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

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

Neuron 5707 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: 1.1801. Min Range: -1.1801

Max Act: 1.1801. Min Act: -0.0000

Data Index: 76899 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 1.1801. Min Range: -1.1801

Max Act: 1.1400. Min Act: -0.0000

Data Index: 1517661 (Python Code)

Max Activating Token Index: 670

Text #2

Max Range: 1.1801. Min Range: -1.1801

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1580248 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 1.1801. Min Range: -1.1801

Max Act: 1.0281. Min Act: -0.0000

Data Index: 1412925 (Python Code)

Max Activating Token Index: 849

Text #4

Max Range: 1.1801. Min Range: -1.1801

Max Act: 1.0331. Min Act: -0.0000

Data Index: 1470545 (Python Code)

Max Activating Token Index: 396

Text #5

Max Range: 1.1801. Min Range: -1.1801

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1549164 (Python Code)

Max Activating Token Index: 847

Text #6

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1624473 (Python Code)

Max Activating Token Index: 229

Text #7

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.9753. Min Act: -0.0000

Data Index: 1635050 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.9393. Min Act: -0.0000

Data Index: 1508968 (Python Code)

Max Activating Token Index: 59

Text #9

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.9306. Min Act: -0.0000

Data Index: 1372470 (Python Code)

Max Activating Token Index: 594

Text #10

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.9652. Min Act: -0.0000

Data Index: 1493850 (Python Code)

Max Activating Token Index: 395

Text #11

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1629474 (Python Code)

Max Activating Token Index: 441

Text #12

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1536508 (Python Code)

Max Activating Token Index: 198

Text #13

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1567197 (Python Code)

Max Activating Token Index: 396

Text #14

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1581501 (Python Code)

Max Activating Token Index: 362

Text #15

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1634419 (Python Code)

Max Activating Token Index: 99

Text #16

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1364657 (Python Code)

Max Activating Token Index: 715

Text #17

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8289. Min Act: -0.0000

Data Index: 439456 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.7295. Min Act: -0.0000

Data Index: 602866 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 1.1801. Min Range: -1.1801

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1591359 (Python Code)

Max Activating Token Index: 106