Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1115 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.7936. Min Act: -0.1700

Data Index: 627684 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.6061. Min Act: -0.1700

Data Index: 1318663 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.5124. Min Act: -0.1700

Data Index: 1352983 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.5124. Min Act: -0.1700

Data Index: 174704 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.4186. Min Act: -0.1700

Data Index: 34649 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.4499. Min Act: -0.1700

Data Index: 337348 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.4811. Min Act: -0.1700

Data Index: 850650 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.4186. Min Act: -0.1700

Data Index: 314126 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.3874. Min Act: -0.1700

Data Index: 1153329 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.3874. Min Act: -0.1700

Data Index: 914212 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.2624. Min Act: -0.1700

Data Index: 1341273 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.3249. Min Act: -0.1700

Data Index: 431373 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.3249. Min Act: -0.1700

Data Index: 1308620 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.3249. Min Act: -0.1700

Data Index: 95281 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.2624. Min Act: -0.1700

Data Index: 367467 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.2624. Min Act: -0.1700

Data Index: 1288200 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.2936. Min Act: -0.1700

Data Index: 859501 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.2624. Min Act: -0.1700

Data Index: 183765 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.2311. Min Act: -0.1700

Data Index: 981770 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 5.7936. Min Range: -5.7936

Max Act: 5.1999. Min Act: -0.1700

Data Index: 219602 (C4 (Web Text))

Max Activating Token Index: 334