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

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

Neuron 682 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: 5.1613. Min Range: -5.1613

Max Act: 5.1613. Min Act: -0.1700

Data Index: 806757 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.7863. Min Act: -0.1700

Data Index: 1302170 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.6925. Min Act: -0.1700

Data Index: 1046050 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.7550. Min Act: -0.1700

Data Index: 284932 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.7238. Min Act: -0.1700

Data Index: 945474 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.6925. Min Act: -0.1700

Data Index: 758625 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.6925. Min Act: -0.1700

Data Index: 859999 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.6613. Min Act: -0.1700

Data Index: 1158551 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.5988. Min Act: -0.1700

Data Index: 821683 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.5675. Min Act: -0.1700

Data Index: 1019741 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.5363. Min Act: -0.1700

Data Index: 244774 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.5675. Min Act: -0.1700

Data Index: 146694 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.5363. Min Act: -0.1700

Data Index: 1251295 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.5988. Min Act: -0.1700

Data Index: 421142 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.4738. Min Act: -0.1700

Data Index: 809702 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.5675. Min Act: -0.1700

Data Index: 980806 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.4425. Min Act: -0.1700

Data Index: 516913 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.4738. Min Act: -0.1700

Data Index: 669541 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.5050. Min Act: -0.1700

Data Index: 1215151 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 5.1613. Min Range: -5.1613

Max Act: 4.3800. Min Act: -0.1700

Data Index: 41394 (C4 (Web Text))

Max Activating Token Index: 912