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

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

Neuron 760 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: 3.4949. Min Range: -3.4949

Max Act: 3.4949. Min Act: -0.1700

Data Index: 1473963 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.4627. Min Act: -0.1700

Data Index: 1617042 (Python Code)

Max Activating Token Index: 911

Text #2

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.4633. Min Act: -0.1700

Data Index: 1629873 (Python Code)

Max Activating Token Index: 442

Text #3

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.4811. Min Act: -0.1700

Data Index: 1539788 (Python Code)

Max Activating Token Index: 169

Text #4

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.4392. Min Act: -0.1699

Data Index: 700252 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.4503. Min Act: -0.1700

Data Index: 1368847 (Python Code)

Max Activating Token Index: 484

Text #6

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.4516. Min Act: -0.1700

Data Index: 1387515 (Python Code)

Max Activating Token Index: 602

Text #7

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.4497. Min Act: -0.1700

Data Index: 1633681 (Python Code)

Max Activating Token Index: 859

Text #8

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.4469. Min Act: -0.1699

Data Index: 273292 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.4611. Min Act: -0.1700

Data Index: 354896 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.3914. Min Act: -0.1700

Data Index: 417578 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.3479. Min Act: -0.1700

Data Index: 657987 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.3078. Min Act: -0.1700

Data Index: 1497669 (Python Code)

Max Activating Token Index: 834

Text #13

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2909. Min Act: -0.1699

Data Index: 1371767 (Python Code)

Max Activating Token Index: 937

Text #14

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2923. Min Act: -0.1700

Data Index: 1583643 (Python Code)

Max Activating Token Index: 170

Text #15

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2667. Min Act: -0.1700

Data Index: 1628244 (Python Code)

Max Activating Token Index: 93

Text #16

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2768. Min Act: -0.1700

Data Index: 1434979 (Python Code)

Max Activating Token Index: 597

Text #17

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2707. Min Act: -0.1699

Data Index: 1553246 (Python Code)

Max Activating Token Index: 456

Text #18

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2547. Min Act: -0.1700

Data Index: 517957 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2438. Min Act: -0.1700

Data Index: 1425644 (Python Code)

Max Activating Token Index: 467