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

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

Neuron 666 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.6842. Min Range: -7.6842

Max Act: 7.6842. Min Act: -0.1700

Data Index: 361520 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 7.6842. Min Range: -7.6842

Max Act: 7.5592. Min Act: -0.1700

Data Index: 1016165 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 7.6842. Min Range: -7.6842

Max Act: 7.3404. Min Act: -0.1700

Data Index: 938967 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 7.6842. Min Range: -7.6842

Max Act: 7.2467. Min Act: -0.1700

Data Index: 1055036 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 7.6842. Min Range: -7.6842

Max Act: 7.1842. Min Act: -0.1700

Data Index: 1210898 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 7.6842. Min Range: -7.6842

Max Act: 7.0592. Min Act: -0.1700

Data Index: 397723 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 7.6842. Min Range: -7.6842

Max Act: 7.0279. Min Act: -0.1700

Data Index: 32667 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 7.6842. Min Range: -7.6842

Max Act: 6.9967. Min Act: -0.1700

Data Index: 918416 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 7.6842. Min Range: -7.6842

Max Act: 7.0279. Min Act: -0.1700

Data Index: 407765 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 7.6842. Min Range: -7.6842

Max Act: 6.9654. Min Act: -0.1700

Data Index: 1301950 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 7.6842. Min Range: -7.6842

Max Act: 6.8717. Min Act: -0.1700

Data Index: 1308014 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 7.6842. Min Range: -7.6842

Max Act: 6.6842. Min Act: -0.1700

Data Index: 1063311 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 7.6842. Min Range: -7.6842

Max Act: 6.6842. Min Act: -0.1700

Data Index: 597531 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 7.6842. Min Range: -7.6842

Max Act: 6.6217. Min Act: -0.1700

Data Index: 1171951 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 7.6842. Min Range: -7.6842

Max Act: 6.6842. Min Act: -0.1700

Data Index: 642369 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 7.6842. Min Range: -7.6842

Max Act: 6.5592. Min Act: -0.1700

Data Index: 647317 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 7.6842. Min Range: -7.6842

Max Act: 6.5279. Min Act: -0.1700

Data Index: 788422 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 7.6842. Min Range: -7.6842

Max Act: 6.6217. Min Act: -0.1700

Data Index: 981654 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 7.6842. Min Range: -7.6842

Max Act: 6.5904. Min Act: -0.1700

Data Index: 892188 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 7.6842. Min Range: -7.6842

Max Act: 6.4029. Min Act: -0.1700

Data Index: 1098880 (C4 (Web Text))

Max Activating Token Index: 828