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

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

Neuron 573 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: 3.5140. Min Range: -3.5140

Max Act: 3.5140. Min Act: -0.1700

Data Index: 833889 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.2158. Min Act: -0.1700

Data Index: 675924 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.2158. Min Act: -0.1700

Data Index: 33531 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.1528. Min Act: -0.1700

Data Index: 1326642 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.1686. Min Act: -0.1700

Data Index: 39983 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.1686. Min Act: -0.1700

Data Index: 650291 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.1371. Min Act: -0.1700

Data Index: 155027 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.1213. Min Act: -0.1700

Data Index: 1041415 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.1371. Min Act: -0.1700

Data Index: 748896 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.1213. Min Act: -0.1700

Data Index: 1013722 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.0740. Min Act: -0.1700

Data Index: 766292 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.1056. Min Act: -0.1700

Data Index: 427066 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.0898. Min Act: -0.1700

Data Index: 691 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.0582. Min Act: -0.1700

Data Index: 1250657 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.0582. Min Act: -0.1700

Data Index: 1053409 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.0425. Min Act: -0.1700

Data Index: 858729 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.0425. Min Act: -0.1700

Data Index: 1228177 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.1213. Min Act: -0.1700

Data Index: 775435 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.0425. Min Act: -0.1699

Data Index: 981154 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 3.5140. Min Range: -3.5140

Max Act: 3.0267. Min Act: -0.1700

Data Index: 411372 (C4 (Web Text))

Max Activating Token Index: 877