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

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

Neuron 210 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.4694. Min Act: -0.0000

Data Index: 1365269 (Python Code)

Max Activating Token Index: 300

Text #1

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.6960. Min Act: -0.0000

Data Index: 1442880 (Python Code)

Max Activating Token Index: 418

Text #2

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.6901. Min Act: -0.0000

Data Index: 1612502 (Python Code)

Max Activating Token Index: 823

Text #3

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.5728. Min Act: -0.0000

Data Index: 1625746 (Python Code)

Max Activating Token Index: 204

Text #4

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.0270. Min Act: -0.0000

Data Index: 1641857 (Python Code)

Max Activating Token Index: 943

Text #5

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.3924. Min Act: -0.0000

Data Index: 1459524 (Python Code)

Max Activating Token Index: 983

Text #6

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.6340. Min Act: -0.0000

Data Index: 1601146 (Python Code)

Max Activating Token Index: 272

Text #7

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.6399. Min Act: -0.0000

Data Index: 1365676 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.2587. Min Act: -0.0000

Data Index: 1523742 (Python Code)

Max Activating Token Index: 388

Text #9

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.4886. Min Act: -0.0000

Data Index: 1470174 (Python Code)

Max Activating Token Index: 528

Text #10

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.6230. Min Act: -0.0000

Data Index: 1463993 (Python Code)

Max Activating Token Index: 34

Text #11

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.4777. Min Act: -0.0000

Data Index: 1517956 (Python Code)

Max Activating Token Index: 947

Text #12

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.1940. Min Act: -0.0000

Data Index: 1595837 (Python Code)

Max Activating Token Index: 704

Text #13

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.2954. Min Act: -0.0000

Data Index: 1561860 (Python Code)

Max Activating Token Index: 633

Text #14

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.3808. Min Act: -0.0000

Data Index: 1630872 (Python Code)

Max Activating Token Index: 457

Text #15

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.2590. Min Act: -0.0000

Data Index: 1399671 (Python Code)

Max Activating Token Index: 483

Text #16

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.2389. Min Act: -0.0000

Data Index: 1413969 (Python Code)

Max Activating Token Index: 342

Text #17

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.2344. Min Act: -0.0000

Data Index: 1576656 (Python Code)

Max Activating Token Index: 431

Text #18

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.4724. Min Act: -0.0000

Data Index: 1637837 (Python Code)

Max Activating Token Index: 391

Text #19

Max Range: 2.6960. Min Range: -2.6960

Max Act: 2.3314. Min Act: -0.0000

Data Index: 1363989 (Python Code)

Max Activating Token Index: 226