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

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

Neuron 1170 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: 3.5559. Min Range: -3.5559

Max Act: 3.5559. Min Act: -0.1697

Data Index: 1644974 (Python Code)

Max Activating Token Index: 798

Text #1

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.5381. Min Act: -0.1700

Data Index: 1379877 (Python Code)

Max Activating Token Index: 296

Text #2

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4287. Min Act: -0.1699

Data Index: 1468320 (Python Code)

Max Activating Token Index: 578

Text #3

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4300. Min Act: -0.1681

Data Index: 1407013 (Python Code)

Max Activating Token Index: 958

Text #4

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.3880. Min Act: -0.1700

Data Index: 1372694 (Python Code)

Max Activating Token Index: 860

Text #5

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.3941. Min Act: -0.1678

Data Index: 1432453 (Python Code)

Max Activating Token Index: 985

Text #6

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.3512. Min Act: -0.1700

Data Index: 530633 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.3514. Min Act: -0.1142

Data Index: 1549473 (Python Code)

Max Activating Token Index: 624

Text #8

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.3142. Min Act: -0.1700

Data Index: 827050 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.2660. Min Act: -0.1691

Data Index: 1630902 (Python Code)

Max Activating Token Index: 427

Text #10

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.3020. Min Act: -0.1686

Data Index: 1430327 (Python Code)

Max Activating Token Index: 99

Text #11

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.2839. Min Act: -0.1699

Data Index: 1493462 (Python Code)

Max Activating Token Index: 733

Text #12

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.2757. Min Act: -0.1679

Data Index: 1366357 (Python Code)

Max Activating Token Index: 812

Text #13

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.2449. Min Act: -0.1644

Data Index: 1650863 (Python Code)

Max Activating Token Index: 477

Text #14

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.2626. Min Act: -0.1698

Data Index: 1517479 (Python Code)

Max Activating Token Index: 790

Text #15

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.2647. Min Act: -0.1690

Data Index: 1287462 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.2180. Min Act: -0.1699

Data Index: 1093981 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.1903. Min Act: -0.1688

Data Index: 1569578 (Python Code)

Max Activating Token Index: 978

Text #18

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.2004. Min Act: -0.1699

Data Index: 1456415 (Python Code)

Max Activating Token Index: 448

Text #19

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.1835. Min Act: -0.1699

Data Index: 1391540 (Python Code)

Max Activating Token Index: 485