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

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

Neuron 1976 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0972. Min Act: -0.1700

Data Index: 884240 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0814. Min Act: -0.1700

Data Index: 1201226 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0814. Min Act: -0.1700

Data Index: 664472 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0498. Min Act: -0.1700

Data Index: 416807 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0498. Min Act: -0.1700

Data Index: 944299 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0656. Min Act: -0.1700

Data Index: 308726 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0656. Min Act: -0.1700

Data Index: 103629 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0340. Min Act: -0.1700

Data Index: 1115657 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0340. Min Act: -0.1700

Data Index: 399110 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0498. Min Act: -0.1700

Data Index: 515120 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0498. Min Act: -0.1700

Data Index: 471056 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0498. Min Act: -0.1700

Data Index: 1247162 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0340. Min Act: -0.1700

Data Index: 1310395 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0498. Min Act: -0.1700

Data Index: 376834 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0182. Min Act: -0.1700

Data Index: 1076074 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0340. Min Act: -0.1700

Data Index: 571216 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0340. Min Act: -0.1700

Data Index: 471587 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0340. Min Act: -0.1700

Data Index: 800495 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0024. Min Act: -0.1700

Data Index: 44921 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 3.0972. Min Range: -3.0972

Max Act: 3.0024. Min Act: -0.1700

Data Index: 90885 (C4 (Web Text))

Max Activating Token Index: 194