Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2856 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.1084. Min Range: -3.1084

Max Act: 3.1084. Min Act: -0.1700

Data Index: 5933374 (Open Web Text)

Max Activating Token Index: 218

Text #1

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.9494. Min Act: -0.1693

Data Index: 1999740 (Open Web Text)

Max Activating Token Index: 982

Text #2

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.8879. Min Act: -0.1698

Data Index: 1081141 (Open Web Text)

Max Activating Token Index: 659

Text #3

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.8342. Min Act: -0.1700

Data Index: 2479005 (Open Web Text)

Max Activating Token Index: 493

Text #4

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.8317. Min Act: -0.1661

Data Index: 1081142 (Open Web Text)

Max Activating Token Index: 754

Text #5

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.8520. Min Act: -0.1693

Data Index: 3618337 (Open Web Text)

Max Activating Token Index: 353

Text #6

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.8128. Min Act: -0.1642

Data Index: 1999750 (Open Web Text)

Max Activating Token Index: 980

Text #7

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.8112. Min Act: -0.1700

Data Index: 4255695 (Open Web Text)

Max Activating Token Index: 395

Text #8

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.7953. Min Act: -0.1700

Data Index: 1999738 (Open Web Text)

Max Activating Token Index: 952

Text #9

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.7844. Min Act: -0.1695

Data Index: 3618324 (Open Web Text)

Max Activating Token Index: 636

Text #10

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.7769. Min Act: -0.1693

Data Index: 3618335 (Open Web Text)

Max Activating Token Index: 975

Text #11

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.7950. Min Act: -0.1700

Data Index: 5009396 (Open Web Text)

Max Activating Token Index: 909

Text #12

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.7907. Min Act: -0.1694

Data Index: 6320427 (Open Web Text)

Max Activating Token Index: 410

Text #13

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.7695. Min Act: -0.1680

Data Index: 1999748 (Open Web Text)

Max Activating Token Index: 909

Text #14

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.7679. Min Act: -0.1700

Data Index: 1999749 (Open Web Text)

Max Activating Token Index: 515

Text #15

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.7735. Min Act: -0.1692

Data Index: 1081143 (Open Web Text)

Max Activating Token Index: 419

Text #16

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.7604. Min Act: -0.1700

Data Index: 1999742 (Open Web Text)

Max Activating Token Index: 445

Text #17

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.7546. Min Act: -0.1673

Data Index: 1999744 (Open Web Text)

Max Activating Token Index: 452

Text #18

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.7493. Min Act: -0.1700

Data Index: 1604571 (Open Web Text)

Max Activating Token Index: 631

Text #19

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.7675. Min Act: -0.1700

Data Index: 6030311 (Open Web Text)

Max Activating Token Index: 1015