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

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

Neuron 1512 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.6424. Min Act: -0.1700

Data Index: 1280227 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.6111. Min Act: -0.1700

Data Index: 375391 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5955. Min Act: -0.1700

Data Index: 1058534 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5955. Min Act: -0.1700

Data Index: 781095 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5955. Min Act: -0.1700

Data Index: 863964 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5798. Min Act: -0.1700

Data Index: 240963 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5955. Min Act: -0.1700

Data Index: 60259 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5641. Min Act: -0.1700

Data Index: 709037 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5641. Min Act: -0.1700

Data Index: 138404 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5485. Min Act: -0.1700

Data Index: 531840 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5172. Min Act: -0.1700

Data Index: 844061 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5328. Min Act: -0.1700

Data Index: 510950 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5328. Min Act: -0.1700

Data Index: 774393 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5328. Min Act: -0.1700

Data Index: 1157918 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5328. Min Act: -0.1700

Data Index: 8378 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5015. Min Act: -0.1700

Data Index: 760729 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5172. Min Act: -0.1700

Data Index: 867392 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5172. Min Act: -0.1700

Data Index: 316067 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5172. Min Act: -0.1700

Data Index: 1173786 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4858. Min Act: -0.1700

Data Index: 597796 (C4 (Web Text))

Max Activating Token Index: 706