Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 162 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 8.7959. Min Range: -8.7959

Max Act: 8.7959. Min Act: -0.1699

Data Index: 1464773 (Python Code)

Max Activating Token Index: 958

Text #1

Max Range: 8.7959. Min Range: -8.7959

Max Act: 8.5459. Min Act: -0.1699

Data Index: 1378556 (Python Code)

Max Activating Token Index: 134

Text #2

Max Range: 8.7959. Min Range: -8.7959

Max Act: 8.6396. Min Act: -0.1699

Data Index: 953089 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 8.7959. Min Range: -8.7959

Max Act: 8.5771. Min Act: -0.1699

Data Index: 1497728 (Python Code)

Max Activating Token Index: 910

Text #4

Max Range: 8.7959. Min Range: -8.7959

Max Act: 8.4521. Min Act: -0.1699

Data Index: 1642016 (Python Code)

Max Activating Token Index: 929

Text #5

Max Range: 8.7959. Min Range: -8.7959

Max Act: 8.4209. Min Act: -0.1699

Data Index: 1413976 (Python Code)

Max Activating Token Index: 492

Text #6

Max Range: 8.7959. Min Range: -8.7959

Max Act: 8.4209. Min Act: -0.1699

Data Index: 1473007 (Python Code)

Max Activating Token Index: 714

Text #7

Max Range: 8.7959. Min Range: -8.7959

Max Act: 8.2959. Min Act: -0.1699

Data Index: 1451701 (Python Code)

Max Activating Token Index: 660

Text #8

Max Range: 8.7959. Min Range: -8.7959

Max Act: 8.2959. Min Act: -0.1699

Data Index: 1423667 (Python Code)

Max Activating Token Index: 864

Text #9

Max Range: 8.7959. Min Range: -8.7959

Max Act: 8.1240. Min Act: -0.1699

Data Index: 1468756 (Python Code)

Max Activating Token Index: 905

Text #10

Max Range: 8.7959. Min Range: -8.7959

Max Act: 8.0771. Min Act: -0.1699

Data Index: 1384622 (Python Code)

Max Activating Token Index: 339

Text #11

Max Range: 8.7959. Min Range: -8.7959

Max Act: 8.1240. Min Act: -0.1699

Data Index: 1619417 (Python Code)

Max Activating Token Index: 935

Text #12

Max Range: 8.7959. Min Range: -8.7959

Max Act: 8.0146. Min Act: -0.1699

Data Index: 1584698 (Python Code)

Max Activating Token Index: 913

Text #13

Max Range: 8.7959. Min Range: -8.7959

Max Act: 7.9053. Min Act: -0.1699

Data Index: 1465745 (Python Code)

Max Activating Token Index: 997

Text #14

Max Range: 8.7959. Min Range: -8.7959

Max Act: 7.9209. Min Act: -0.1699

Data Index: 1462024 (Python Code)

Max Activating Token Index: 991

Text #15

Max Range: 8.7959. Min Range: -8.7959

Max Act: 7.8896. Min Act: -0.1699

Data Index: 1390903 (Python Code)

Max Activating Token Index: 982

Text #16

Max Range: 8.7959. Min Range: -8.7959

Max Act: 7.8115. Min Act: -0.1699

Data Index: 76633 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 8.7959. Min Range: -8.7959

Max Act: 7.9053. Min Act: -0.1699

Data Index: 518966 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 8.7959. Min Range: -8.7959

Max Act: 7.8584. Min Act: -0.1699

Data Index: 1576882 (Python Code)

Max Activating Token Index: 835

Text #19

Max Range: 8.7959. Min Range: -8.7959

Max Act: 7.8740. Min Act: -0.1699

Data Index: 1651511 (Python Code)

Max Activating Token Index: 698