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

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

Neuron 454 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.3151. Min Act: -0.1700

Data Index: 711852 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.3464. Min Act: -0.1700

Data Index: 60118 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.2839. Min Act: -0.1700

Data Index: 1147706 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.3151. Min Act: -0.1700

Data Index: 769933 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.2526. Min Act: -0.1700

Data Index: 452825 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.2526. Min Act: -0.1700

Data Index: 1208049 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.2526. Min Act: -0.1700

Data Index: 73295 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.2526. Min Act: -0.1700

Data Index: 858501 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.2057. Min Act: -0.1700

Data Index: 535434 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.2370. Min Act: -0.1700

Data Index: 372813 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.2370. Min Act: -0.1700

Data Index: 562764 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.1901. Min Act: -0.1700

Data Index: 1059279 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.2526. Min Act: -0.1700

Data Index: 1216419 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.1901. Min Act: -0.1700

Data Index: 1295068 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.2214. Min Act: -0.1700

Data Index: 1200930 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.1901. Min Act: -0.1700

Data Index: 1186668 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.1745. Min Act: -0.1700

Data Index: 1187029 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.1432. Min Act: -0.1700

Data Index: 360308 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.1589. Min Act: -0.1700

Data Index: 669526 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.1745. Min Act: -0.1700

Data Index: 1233956 (C4 (Web Text))

Max Activating Token Index: 56