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

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

Neuron 1984 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: 5.3493. Min Range: -5.3493

Max Act: 5.3493. Min Act: -0.1700

Data Index: 205762 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.3493. Min Act: -0.1700

Data Index: 41218 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.3181. Min Act: -0.1700

Data Index: 562535 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.3181. Min Act: -0.1700

Data Index: 311076 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.2556. Min Act: -0.1700

Data Index: 1289616 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.2868. Min Act: -0.1700

Data Index: 521183 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.2556. Min Act: -0.1700

Data Index: 1103185 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.2556. Min Act: -0.1700

Data Index: 90106 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.2243. Min Act: -0.1700

Data Index: 714257 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.2243. Min Act: -0.1700

Data Index: 598162 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.2243. Min Act: -0.1700

Data Index: 838544 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.1931. Min Act: -0.1700

Data Index: 592421 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.2243. Min Act: -0.1700

Data Index: 527497 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.2243. Min Act: -0.1700

Data Index: 809330 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.1931. Min Act: -0.1700

Data Index: 808002 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.2243. Min Act: -0.1700

Data Index: 202019 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.2243. Min Act: -0.1700

Data Index: 968883 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.2243. Min Act: -0.1700

Data Index: 102384 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.2556. Min Act: -0.1700

Data Index: 953469 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 5.3493. Min Range: -5.3493

Max Act: 5.2243. Min Act: -0.1700

Data Index: 122680 (C4 (Web Text))

Max Activating Token Index: 738