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

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

Neuron 1991 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: 3.2612. Min Range: -3.2612

Max Act: 3.2612. Min Act: -0.1700

Data Index: 268457 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.2455. Min Act: -0.1700

Data Index: 986873 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1983. Min Act: -0.1700

Data Index: 999116 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1983. Min Act: -0.1700

Data Index: 58585 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1826. Min Act: -0.1700

Data Index: 1189853 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1826. Min Act: -0.1700

Data Index: 510051 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1668. Min Act: -0.1700

Data Index: 916473 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1353. Min Act: -0.1700

Data Index: 976033 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1196. Min Act: -0.1700

Data Index: 1154620 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1511. Min Act: -0.1700

Data Index: 890329 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1353. Min Act: -0.1700

Data Index: 718612 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1353. Min Act: -0.1700

Data Index: 452367 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1196. Min Act: -0.1700

Data Index: 1122450 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1038. Min Act: -0.1700

Data Index: 907715 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1353. Min Act: -0.1700

Data Index: 612652 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1353. Min Act: -0.1700

Data Index: 617092 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1038. Min Act: -0.1700

Data Index: 783172 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1196. Min Act: -0.1700

Data Index: 716092 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1511. Min Act: -0.1700

Data Index: 1294872 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 3.2612. Min Range: -3.2612

Max Act: 3.1353. Min Act: -0.1700

Data Index: 562849 (C4 (Web Text))

Max Activating Token Index: 395