Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 809 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.6133. Min Act: -0.1700

Data Index: 383578 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.5976. Min Act: -0.1700

Data Index: 1242290 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.5663. Min Act: -0.1700

Data Index: 831033 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.5506. Min Act: -0.1700

Data Index: 1643497 (Python Code)

Max Activating Token Index: 116

Text #4

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.5506. Min Act: -0.1700

Data Index: 817505 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.5193. Min Act: -0.1700

Data Index: 434749 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.5193. Min Act: -0.1700

Data Index: 282786 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.5036. Min Act: -0.1700

Data Index: 104181 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.4880. Min Act: -0.1700

Data Index: 547438 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.5036. Min Act: -0.1700

Data Index: 1072071 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.5036. Min Act: -0.1700

Data Index: 713930 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.4723. Min Act: -0.1700

Data Index: 768201 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.4723. Min Act: -0.1700

Data Index: 430054 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.4566. Min Act: -0.1700

Data Index: 1054193 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.4409. Min Act: -0.1700

Data Index: 969852 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.4409. Min Act: -0.1700

Data Index: 1181140 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.4566. Min Act: -0.1700

Data Index: 34422 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.4253. Min Act: -0.1700

Data Index: 716114 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.4253. Min Act: -0.1700

Data Index: 1013992 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 3.6133. Min Range: -3.6133

Max Act: 3.4409. Min Act: -0.1700

Data Index: 354375 (C4 (Web Text))

Max Activating Token Index: 546