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

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

Neuron 1802 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: 3.9863. Min Range: -3.9863

Max Act: 3.9863. Min Act: -0.1700

Data Index: 919775 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8925. Min Act: -0.1700

Data Index: 503035 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8299. Min Act: -0.1700

Data Index: 356035 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8612. Min Act: -0.1700

Data Index: 1343081 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8299. Min Act: -0.1700

Data Index: 1185541 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8299. Min Act: -0.1700

Data Index: 1247473 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.7986. Min Act: -0.1700

Data Index: 189087 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.8299. Min Act: -0.1700

Data Index: 1207707 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.7674. Min Act: -0.1700

Data Index: 1234581 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.7986. Min Act: -0.1700

Data Index: 557724 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.7986. Min Act: -0.1700

Data Index: 252476 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.7674. Min Act: -0.1700

Data Index: 244684 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.7361. Min Act: -0.1700

Data Index: 60643 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.7361. Min Act: -0.1700

Data Index: 448135 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.7048. Min Act: -0.1700

Data Index: 287848 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.7361. Min Act: -0.1700

Data Index: 570987 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.7361. Min Act: -0.1700

Data Index: 1254313 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.7674. Min Act: -0.1700

Data Index: 1129956 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.7986. Min Act: -0.1700

Data Index: 729111 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 3.9863. Min Range: -3.9863

Max Act: 3.7361. Min Act: -0.1700

Data Index: 869329 (C4 (Web Text))

Max Activating Token Index: 81