Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 343 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.6096. Min Act: -0.1700

Data Index: 567502 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.6409. Min Act: -0.1700

Data Index: 87908 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.6096. Min Act: -0.1700

Data Index: 1194607 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.5470. Min Act: -0.1700

Data Index: 966057 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.5470. Min Act: -0.1700

Data Index: 1082525 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.5156. Min Act: -0.1700

Data Index: 140579 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.5156. Min Act: -0.1700

Data Index: 1252444 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4529. Min Act: -0.1700

Data Index: 500185 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.5156. Min Act: -0.1700

Data Index: 537309 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.5470. Min Act: -0.1700

Data Index: 1033577 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4843. Min Act: -0.1700

Data Index: 48547 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4529. Min Act: -0.1700

Data Index: 803377 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4843. Min Act: -0.1700

Data Index: 156827 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4529. Min Act: -0.1700

Data Index: 1063973 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4529. Min Act: -0.1700

Data Index: 723155 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4529. Min Act: -0.1700

Data Index: 83519 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4843. Min Act: -0.1700

Data Index: 1202747 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4529. Min Act: -0.1700

Data Index: 98751 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4216. Min Act: -0.1700

Data Index: 72599 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.4216. Min Act: -0.1700

Data Index: 674347 (C4 (Web Text))

Max Activating Token Index: 813