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

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

Neuron 963 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.3554. Min Range: -5.3554

Max Act: 5.3554. Min Act: -0.1700

Data Index: 554586 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 5.3554. Min Range: -5.3554

Max Act: 5.2929. Min Act: -0.1700

Data Index: 622982 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 5.3554. Min Range: -5.3554

Max Act: 5.1054. Min Act: -0.1700

Data Index: 51848 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 5.3554. Min Range: -5.3554

Max Act: 5.1367. Min Act: -0.1700

Data Index: 973187 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 5.3554. Min Range: -5.3554

Max Act: 5.0117. Min Act: -0.1700

Data Index: 221514 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 5.3554. Min Range: -5.3554

Max Act: 5.0117. Min Act: -0.1700

Data Index: 507364 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 5.3554. Min Range: -5.3554

Max Act: 5.0117. Min Act: -0.1700

Data Index: 1156511 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 5.3554. Min Range: -5.3554

Max Act: 5.0117. Min Act: -0.1700

Data Index: 682397 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 5.3554. Min Range: -5.3554

Max Act: 5.1054. Min Act: -0.1700

Data Index: 1233220 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 5.3554. Min Range: -5.3554

Max Act: 4.9492. Min Act: -0.1700

Data Index: 1050133 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 5.3554. Min Range: -5.3554

Max Act: 4.9648. Min Act: -0.1700

Data Index: 1355852 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 5.3554. Min Range: -5.3554

Max Act: 4.9492. Min Act: -0.1700

Data Index: 179341 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 5.3554. Min Range: -5.3554

Max Act: 4.9179. Min Act: -0.1700

Data Index: 928072 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 5.3554. Min Range: -5.3554

Max Act: 4.9179. Min Act: -0.1700

Data Index: 245028 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 5.3554. Min Range: -5.3554

Max Act: 4.9804. Min Act: -0.1700

Data Index: 331300 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 5.3554. Min Range: -5.3554

Max Act: 4.8554. Min Act: -0.1700

Data Index: 312538 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 5.3554. Min Range: -5.3554

Max Act: 4.8242. Min Act: -0.1700

Data Index: 372011 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 5.3554. Min Range: -5.3554

Max Act: 4.9023. Min Act: -0.1700

Data Index: 1293604 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 5.3554. Min Range: -5.3554

Max Act: 4.9023. Min Act: -0.1700

Data Index: 319607 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 5.3554. Min Range: -5.3554

Max Act: 4.8867. Min Act: -0.1700

Data Index: 998029 (C4 (Web Text))

Max Activating Token Index: 728