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

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

Neuron 445 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: 5.7382. Min Range: -5.7382

Max Act: 5.7382. Min Act: -0.1700

Data Index: 333758 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.6445. Min Act: -0.1700

Data Index: 1086487 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.5507. Min Act: -0.1700

Data Index: 1656069 (Python Code)

Max Activating Token Index: 59

Text #3

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.5195. Min Act: -0.1700

Data Index: 1264549 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.4570. Min Act: -0.1700

Data Index: 413314 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.4882. Min Act: -0.1700

Data Index: 302675 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.3007. Min Act: -0.1700

Data Index: 153758 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.3320. Min Act: -0.1700

Data Index: 353977 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.2695. Min Act: -0.1700

Data Index: 1173302 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.2695. Min Act: -0.1700

Data Index: 207194 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.3320. Min Act: -0.1700

Data Index: 815225 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 5.7382. Min Range: -5.7382

Max Act: 4.9257. Min Act: -0.1700

Data Index: 110034 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.2695. Min Act: -0.1700

Data Index: 304581 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.2070. Min Act: -0.1700

Data Index: 385883 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.2695. Min Act: -0.1700

Data Index: 449214 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.2382. Min Act: -0.1700

Data Index: 275902 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.2382. Min Act: -0.1700

Data Index: 1341335 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.1132. Min Act: -0.1700

Data Index: 1291652 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.1445. Min Act: -0.1700

Data Index: 571039 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.1757. Min Act: -0.1700

Data Index: 1637013 (Python Code)

Max Activating Token Index: 951