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

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

Neuron 873 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: 5.7895. Min Range: -5.7895

Max Act: 5.7895. Min Act: -0.1700

Data Index: 1282128 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.6020. Min Act: -0.1700

Data Index: 1258983 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.5082. Min Act: -0.1700

Data Index: 227374 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.5082. Min Act: -0.1700

Data Index: 1304842 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.4145. Min Act: -0.1700

Data Index: 99223 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.4145. Min Act: -0.1700

Data Index: 754917 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.4145. Min Act: -0.1700

Data Index: 346152 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.3832. Min Act: -0.1700

Data Index: 835017 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.3832. Min Act: -0.1700

Data Index: 557107 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.3520. Min Act: -0.1700

Data Index: 1006005 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.3520. Min Act: -0.1700

Data Index: 69166 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.3832. Min Act: -0.1700

Data Index: 1208523 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.2582. Min Act: -0.1700

Data Index: 156068 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.3832. Min Act: -0.1700

Data Index: 849094 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.2895. Min Act: -0.1700

Data Index: 420123 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.2895. Min Act: -0.1700

Data Index: 141691 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.2582. Min Act: -0.1700

Data Index: 492224 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.2582. Min Act: -0.1700

Data Index: 317780 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.1957. Min Act: -0.1700

Data Index: 1124399 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 5.7895. Min Range: -5.7895

Max Act: 5.1957. Min Act: -0.1700

Data Index: 871382 (C4 (Web Text))

Max Activating Token Index: 470