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

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

Neuron 3692 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1385. Min Range: -2.1385

Max Act: 2.1385. Min Act: -0.0000

Data Index: 1450539 (Python Code)

Max Activating Token Index: 498

Text #1

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.7250. Min Act: -0.0000

Data Index: 1556891 (Python Code)

Max Activating Token Index: 815

Text #2

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.4963. Min Act: -0.0000

Data Index: 1494129 (Python Code)

Max Activating Token Index: 351

Text #3

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.4282. Min Act: -0.0000

Data Index: 1423801 (Python Code)

Max Activating Token Index: 579

Text #4

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.5093. Min Act: -0.0000

Data Index: 493760 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.4146. Min Act: -0.0000

Data Index: 1082038 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.3433. Min Act: -0.0000

Data Index: 1489941 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.2886. Min Act: -0.0000

Data Index: 919330 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.3164. Min Act: -0.0000

Data Index: 1006651 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.2641. Min Act: -0.0000

Data Index: 981867 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.2617. Min Act: -0.0000

Data Index: 1577974 (Python Code)

Max Activating Token Index: 88

Text #11

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.3381. Min Act: -0.0000

Data Index: 1537639 (Python Code)

Max Activating Token Index: 77

Text #12

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.3242. Min Act: -0.0000

Data Index: 377672 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.3442. Min Act: -0.0000

Data Index: 482464 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.2775. Min Act: -0.0000

Data Index: 1504201 (Python Code)

Max Activating Token Index: 659

Text #15

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.2674. Min Act: -0.0000

Data Index: 1006410 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.2450. Min Act: -0.0000

Data Index: 256287 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.2715. Min Act: -0.0000

Data Index: 1581109 (Python Code)

Max Activating Token Index: 210

Text #18

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.2382. Min Act: -0.0000

Data Index: 766870 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 2.1385. Min Range: -2.1385

Max Act: 1.1626. Min Act: -0.0000

Data Index: 659310 (C4 (Web Text))

Max Activating Token Index: 310