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

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

Neuron 1415 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: 5.4897. Min Range: -5.4897

Max Act: 5.4897. Min Act: -0.1700

Data Index: 1379749 (Python Code)

Max Activating Token Index: 528

Text #1

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.3647. Min Act: -0.1700

Data Index: 1551347 (Python Code)

Max Activating Token Index: 415

Text #2

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.3959. Min Act: -0.1700

Data Index: 1653995 (Python Code)

Max Activating Token Index: 802

Text #3

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.3334. Min Act: -0.1699

Data Index: 1501881 (Python Code)

Max Activating Token Index: 425

Text #4

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.3022. Min Act: -0.1700

Data Index: 1457719 (Python Code)

Max Activating Token Index: 845

Text #5

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.3022. Min Act: -0.1700

Data Index: 1401198 (Python Code)

Max Activating Token Index: 182

Text #6

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.3022. Min Act: -0.1700

Data Index: 1506463 (Python Code)

Max Activating Token Index: 969

Text #7

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.2709. Min Act: -0.1700

Data Index: 1514206 (Python Code)

Max Activating Token Index: 553

Text #8

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.2709. Min Act: -0.1699

Data Index: 1520318 (Python Code)

Max Activating Token Index: 147

Text #9

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.1459. Min Act: -0.1700

Data Index: 1621579 (Python Code)

Max Activating Token Index: 574

Text #10

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.1147. Min Act: -0.1700

Data Index: 1530695 (Python Code)

Max Activating Token Index: 84

Text #11

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.1459. Min Act: -0.1700

Data Index: 1384740 (Python Code)

Max Activating Token Index: 553

Text #12

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.1459. Min Act: -0.1700

Data Index: 1405348 (Python Code)

Max Activating Token Index: 215

Text #13

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.1147. Min Act: -0.1700

Data Index: 1531722 (Python Code)

Max Activating Token Index: 887

Text #14

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.0834. Min Act: -0.1700

Data Index: 1474374 (Python Code)

Max Activating Token Index: 287

Text #15

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.1147. Min Act: -0.1700

Data Index: 1638598 (Python Code)

Max Activating Token Index: 1020

Text #16

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.1147. Min Act: -0.1700

Data Index: 1627949 (Python Code)

Max Activating Token Index: 711

Text #17

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.0834. Min Act: -0.1700

Data Index: 1586037 (Python Code)

Max Activating Token Index: 408

Text #18

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.0522. Min Act: -0.1699

Data Index: 1499748 (Python Code)

Max Activating Token Index: 44

Text #19

Max Range: 5.4897. Min Range: -5.4897

Max Act: 5.0834. Min Act: -0.1700

Data Index: 1584432 (Python Code)

Max Activating Token Index: 741