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

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

Neuron 1796 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: 3.6124. Min Range: -3.6124

Max Act: 3.6124. Min Act: -0.1700

Data Index: 916293 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.5811. Min Act: -0.1700

Data Index: 748595 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.5498. Min Act: -0.1700

Data Index: 695437 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.4871. Min Act: -0.1700

Data Index: 332318 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.5184. Min Act: -0.1700

Data Index: 587201 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.5498. Min Act: -0.1700

Data Index: 14666 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.4558. Min Act: -0.1700

Data Index: 793797 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.3930. Min Act: -0.1700

Data Index: 820070 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.4244. Min Act: -0.1700

Data Index: 1110082 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.4244. Min Act: -0.1700

Data Index: 1195524 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.4244. Min Act: -0.1700

Data Index: 401778 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.3930. Min Act: -0.1700

Data Index: 969912 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.4244. Min Act: -0.1700

Data Index: 448506 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.4558. Min Act: -0.1700

Data Index: 1213023 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.3617. Min Act: -0.1700

Data Index: 24809 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.3930. Min Act: -0.1700

Data Index: 671501 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.3930. Min Act: -0.1700

Data Index: 23578 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.3930. Min Act: -0.1700

Data Index: 738277 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.3930. Min Act: -0.1700

Data Index: 424608 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 3.6124. Min Range: -3.6124

Max Act: 3.3930. Min Act: -0.1700

Data Index: 765575 (C4 (Web Text))

Max Activating Token Index: 565