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

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

Neuron 1551 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.9522. Min Act: -0.0000

Data Index: 706591 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.7963. Min Act: -0.0000

Data Index: 595169 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.9049. Min Act: -0.0000

Data Index: 553269 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.4530. Min Act: -0.0000

Data Index: 427501 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.3239. Min Act: -0.0000

Data Index: 1283430 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.3306. Min Act: -0.0000

Data Index: 936811 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.2706. Min Act: -0.0000

Data Index: 446692 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.1620. Min Act: -0.0000

Data Index: 1140517 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.2510. Min Act: -0.0000

Data Index: 879980 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.2468. Min Act: -0.0000

Data Index: 389121 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.2369. Min Act: -0.0000

Data Index: 1001434 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.3195. Min Act: -0.0000

Data Index: 65453 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.2838. Min Act: -0.0000

Data Index: 387826 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.1362. Min Act: -0.0000

Data Index: 937427 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.1113. Min Act: -0.0000

Data Index: 66346 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.0641. Min Act: -0.0000

Data Index: 440962 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.1762. Min Act: -0.0000

Data Index: 178674 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.1627. Min Act: -0.0000

Data Index: 1096371 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.1347. Min Act: -0.0000

Data Index: 292725 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 2.9522. Min Range: -2.9522

Max Act: 2.0269. Min Act: -0.0000

Data Index: 51853 (C4 (Web Text))

Max Activating Token Index: 255