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

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

Neuron 2044 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: 3.3522. Min Range: -3.3522

Max Act: 3.3522. Min Act: -0.1700

Data Index: 549794 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2737. Min Act: -0.1700

Data Index: 1329058 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2580. Min Act: -0.1700

Data Index: 1315873 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2422. Min Act: -0.1700

Data Index: 557625 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2580. Min Act: -0.1700

Data Index: 810319 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2422. Min Act: -0.1700

Data Index: 607406 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2580. Min Act: -0.1700

Data Index: 276137 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2422. Min Act: -0.1700

Data Index: 1263548 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2422. Min Act: -0.1700

Data Index: 247079 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2422. Min Act: -0.1700

Data Index: 116501 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2422. Min Act: -0.1700

Data Index: 991478 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2265. Min Act: -0.1700

Data Index: 1302001 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2108. Min Act: -0.1700

Data Index: 161318 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2108. Min Act: -0.1700

Data Index: 500228 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2108. Min Act: -0.1700

Data Index: 224559 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.2108. Min Act: -0.1700

Data Index: 1069961 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.1951. Min Act: -0.1700

Data Index: 1313794 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.1951. Min Act: -0.1700

Data Index: 815244 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.1951. Min Act: -0.1700

Data Index: 559938 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 3.3522. Min Range: -3.3522

Max Act: 3.1951. Min Act: -0.1700

Data Index: 366527 (C4 (Web Text))

Max Activating Token Index: 747