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

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

Neuron 4556 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1472879 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1401351 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1403205 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1375682 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1400843 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1601065 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1631427 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1637835 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1407223 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1417401 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1523077 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1523896 (Python Code)

Max Activating Token Index: 2

Text #12

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1534418 (Python Code)

Max Activating Token Index: 2

Text #13

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1652795 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1514040 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1589297 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1433651 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1420014 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1493494 (Python Code)

Max Activating Token Index: 2

Text #19

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1593624 (Python Code)

Max Activating Token Index: 4