Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 499 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.9572. Min Act: -0.1700

Data Index: 1380233 (Python Code)

Max Activating Token Index: 470

Text #1

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.9259. Min Act: -0.1700

Data Index: 1633461 (Python Code)

Max Activating Token Index: 739

Text #2

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.8322. Min Act: -0.1699

Data Index: 1408545 (Python Code)

Max Activating Token Index: 460

Text #3

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.8009. Min Act: -0.1700

Data Index: 1365965 (Python Code)

Max Activating Token Index: 999

Text #4

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.7384. Min Act: -0.1700

Data Index: 1590370 (Python Code)

Max Activating Token Index: 707

Text #5

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.7384. Min Act: -0.1700

Data Index: 1514051 (Python Code)

Max Activating Token Index: 316

Text #6

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.6134. Min Act: -0.1700

Data Index: 1612502 (Python Code)

Max Activating Token Index: 829

Text #7

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.6759. Min Act: -0.1700

Data Index: 1362467 (Python Code)

Max Activating Token Index: 663

Text #8

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.6134. Min Act: -0.1699

Data Index: 1612446 (Python Code)

Max Activating Token Index: 718

Text #9

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.6134. Min Act: -0.1700

Data Index: 1376878 (Python Code)

Max Activating Token Index: 754

Text #10

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.6134. Min Act: -0.1700

Data Index: 1465910 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.5197. Min Act: -0.1699

Data Index: 1511492 (Python Code)

Max Activating Token Index: 637

Text #12

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.4884. Min Act: -0.1700

Data Index: 1365269 (Python Code)

Max Activating Token Index: 306

Text #13

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.4884. Min Act: -0.1700

Data Index: 1642585 (Python Code)

Max Activating Token Index: 460

Text #14

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.4572. Min Act: -0.1700

Data Index: 1654885 (Python Code)

Max Activating Token Index: 248

Text #15

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.3947. Min Act: -0.1700

Data Index: 1406634 (Python Code)

Max Activating Token Index: 908

Text #16

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.4259. Min Act: -0.1700

Data Index: 1595246 (Python Code)

Max Activating Token Index: 987

Text #17

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.3634. Min Act: -0.1700

Data Index: 1415957 (Python Code)

Max Activating Token Index: 528

Text #18

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.3947. Min Act: -0.1699

Data Index: 1505210 (Python Code)

Max Activating Token Index: 297

Text #19

Max Range: 5.9572. Min Range: -5.9572

Max Act: 5.3634. Min Act: -0.1700

Data Index: 1515618 (Python Code)

Max Activating Token Index: 590