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

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

Neuron 607 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: 2.9405. Min Range: -2.9405

Max Act: 2.9405. Min Act: 0.0001

Data Index: 1572318 (Python Code)

Max Activating Token Index: 355

Text #1

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.9353. Min Act: -0.0000

Data Index: 1455403 (Python Code)

Max Activating Token Index: 984

Text #2

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.7807. Min Act: 0.0000

Data Index: 1386850 (Python Code)

Max Activating Token Index: 927

Text #3

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.6405. Min Act: 0.0000

Data Index: 1412738 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.7139. Min Act: -0.0000

Data Index: 1631633 (Python Code)

Max Activating Token Index: 712

Text #5

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.8335. Min Act: -0.0000

Data Index: 1648336 (Python Code)

Max Activating Token Index: 176

Text #6

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.5435. Min Act: 0.0001

Data Index: 1379821 (Python Code)

Max Activating Token Index: 581

Text #7

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.7494. Min Act: -0.0000

Data Index: 1365049 (Python Code)

Max Activating Token Index: 116

Text #8

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.5524. Min Act: 0.0001

Data Index: 1574637 (Python Code)

Max Activating Token Index: 532

Text #9

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.2991. Min Act: 0.0000

Data Index: 1533150 (Python Code)

Max Activating Token Index: 348

Text #10

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.3837. Min Act: 0.0000

Data Index: 1622006 (Python Code)

Max Activating Token Index: 595

Text #11

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.3474. Min Act: 0.0000

Data Index: 1611428 (Python Code)

Max Activating Token Index: 142

Text #12

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.2457. Min Act: 0.0000

Data Index: 1511650 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.4932. Min Act: 0.0001

Data Index: 1512294 (Python Code)

Max Activating Token Index: 250

Text #14

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.3317. Min Act: 0.0000

Data Index: 1379963 (Python Code)

Max Activating Token Index: 464

Text #15

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.3368. Min Act: -0.0000

Data Index: 1622353 (Python Code)

Max Activating Token Index: 676

Text #16

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.1836. Min Act: -0.0000

Data Index: 1574251 (Python Code)

Max Activating Token Index: 310

Text #17

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.2902. Min Act: 0.0002

Data Index: 1474260 (Python Code)

Max Activating Token Index: 42

Text #18

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.1805. Min Act: -0.0000

Data Index: 1459645 (Python Code)

Max Activating Token Index: 790

Text #19

Max Range: 2.9405. Min Range: -2.9405

Max Act: 2.2849. Min Act: -0.0000

Data Index: 1419785 (Python Code)

Max Activating Token Index: 299