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

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

Neuron 203 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: 5.0590. Min Range: -5.0590

Max Act: 5.0590. Min Act: -0.1700

Data Index: 570605 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.8090. Min Act: -0.1700

Data Index: 97691 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.7778. Min Act: -0.1700

Data Index: 1131815 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.8090. Min Act: -0.1700

Data Index: 39234 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.7778. Min Act: -0.1700

Data Index: 1344344 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.7153. Min Act: -0.1700

Data Index: 595162 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.6840. Min Act: -0.1700

Data Index: 765891 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.7465. Min Act: -0.1700

Data Index: 63232 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.6215. Min Act: -0.1700

Data Index: 715768 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.6527. Min Act: -0.1700

Data Index: 671702 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.6527. Min Act: -0.1700

Data Index: 824492 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.6215. Min Act: -0.1700

Data Index: 573442 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.6215. Min Act: -0.1700

Data Index: 1066056 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.5590. Min Act: -0.1700

Data Index: 31223 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.5902. Min Act: -0.1699

Data Index: 1254770 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.5902. Min Act: -0.1700

Data Index: 399914 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.6527. Min Act: -0.1700

Data Index: 676622 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.6527. Min Act: -0.1700

Data Index: 266931 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.7778. Min Act: -0.1700

Data Index: 1289199 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 5.0590. Min Range: -5.0590

Max Act: 4.6527. Min Act: -0.1700

Data Index: 646571 (C4 (Web Text))

Max Activating Token Index: 467