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

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

Neuron 174 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: 5.4393. Min Range: -5.4393

Max Act: 5.4393. Min Act: -0.1700

Data Index: 353642 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.4393. Min Act: -0.1700

Data Index: 332665 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.4080. Min Act: -0.1700

Data Index: 723551 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.3455. Min Act: -0.1700

Data Index: 933179 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.3768. Min Act: -0.1700

Data Index: 873824 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.3768. Min Act: -0.1700

Data Index: 328827 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.3143. Min Act: -0.1700

Data Index: 779734 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.3143. Min Act: -0.1700

Data Index: 1198701 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.3768. Min Act: -0.1700

Data Index: 847735 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.3143. Min Act: -0.1700

Data Index: 490791 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.3143. Min Act: -0.1700

Data Index: 383299 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.2830. Min Act: -0.1700

Data Index: 1309421 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.2518. Min Act: -0.1700

Data Index: 165578 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.2830. Min Act: -0.1700

Data Index: 191553 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.2830. Min Act: -0.1700

Data Index: 128015 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.2205. Min Act: -0.1700

Data Index: 583364 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.3143. Min Act: -0.1700

Data Index: 1301100 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.3143. Min Act: -0.1700

Data Index: 409144 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.2518. Min Act: -0.1700

Data Index: 25617 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 5.4393. Min Range: -5.4393

Max Act: 5.2830. Min Act: -0.1700

Data Index: 929354 (C4 (Web Text))

Max Activating Token Index: 15