Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 787 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.8840. Min Act: -0.1699

Data Index: 1445995 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7842. Min Act: -0.1700

Data Index: 1372472 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7541. Min Act: -0.1700

Data Index: 951597 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7557. Min Act: -0.1695

Data Index: 732955 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7473. Min Act: -0.1700

Data Index: 1655850 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7378. Min Act: -0.1700

Data Index: 786714 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7275. Min Act: -0.1700

Data Index: 655279 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7042. Min Act: -0.1694

Data Index: 1525942 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6935. Min Act: -0.1697

Data Index: 1383547 (Python Code)

Max Activating Token Index: 58

Text #9

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6713. Min Act: -0.1700

Data Index: 511494 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6711. Min Act: -0.1699

Data Index: 1462276 (Python Code)

Max Activating Token Index: 71

Text #11

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6684. Min Act: -0.1700

Data Index: 342787 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6633. Min Act: -0.1700

Data Index: 1282903 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6477. Min Act: -0.1700

Data Index: 856890 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6557. Min Act: -0.1699

Data Index: 1288330 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6422. Min Act: -0.1700

Data Index: 1350614 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6384. Min Act: -0.1700

Data Index: 1394953 (Python Code)

Max Activating Token Index: 39

Text #17

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6289. Min Act: -0.1700

Data Index: 182521 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6334. Min Act: -0.1693

Data Index: 542097 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6215. Min Act: -0.1700

Data Index: 107763 (C4 (Web Text))

Max Activating Token Index: 622