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

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

Neuron 3576 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3506. Min Range: -2.3506

Max Act: 2.3506. Min Act: -0.0000

Data Index: 1315217 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 2.3506. Min Range: -2.3506

Max Act: 2.2866. Min Act: -0.0000

Data Index: 268316 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 2.3506. Min Range: -2.3506

Max Act: 2.2690. Min Act: -0.0000

Data Index: 1009651 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.9336. Min Act: -0.0000

Data Index: 63383 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 2.3506. Min Range: -2.3506

Max Act: 2.1463. Min Act: -0.0000

Data Index: 431873 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 2.3506. Min Range: -2.3506

Max Act: 2.2485. Min Act: -0.0000

Data Index: 1279984 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 2.3506. Min Range: -2.3506

Max Act: 2.0565. Min Act: -0.0000

Data Index: 211978 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 2.3506. Min Range: -2.3506

Max Act: 2.0444. Min Act: -0.0000

Data Index: 940307 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.8256. Min Act: -0.0000

Data Index: 1595034 (Python Code)

Max Activating Token Index: 514

Text #9

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.7489. Min Act: -0.0000

Data Index: 1415875 (Python Code)

Max Activating Token Index: 334

Text #10

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.5926. Min Act: -0.0000

Data Index: 1544628 (Python Code)

Max Activating Token Index: 330

Text #11

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.5692. Min Act: -0.0000

Data Index: 1445839 (Python Code)

Max Activating Token Index: 487

Text #12

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.3767. Min Act: -0.0000

Data Index: 1594640 (Python Code)

Max Activating Token Index: 653

Text #13

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.4029. Min Act: -0.0000

Data Index: 1497601 (Python Code)

Max Activating Token Index: 175

Text #14

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.3953. Min Act: -0.0000

Data Index: 1456192 (Python Code)

Max Activating Token Index: 585

Text #15

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.3481. Min Act: -0.0000

Data Index: 1431020 (Python Code)

Max Activating Token Index: 19

Text #16

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.4174. Min Act: -0.0000

Data Index: 1498957 (Python Code)

Max Activating Token Index: 727

Text #17

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.2266. Min Act: -0.0000

Data Index: 94737 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.3388. Min Act: -0.0000

Data Index: 172815 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.3007. Min Act: -0.0000

Data Index: 1457448 (Python Code)

Max Activating Token Index: 13