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

Dataset: Open Web Text

Neuron 811 in Layer 2

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: 1.7495. Min Range: -1.7495

Max Act: 1.7443. Min Act: -0.1700

Data Index: 3945069 (Open Web Text)

Max Activating Token Index: 916

Text #1

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.7495. Min Act: -0.1699

Data Index: 8494637 (Open Web Text)

Max Activating Token Index: 347

Text #2

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.7407. Min Act: -0.1700

Data Index: 5799623 (Open Web Text)

Max Activating Token Index: 537

Text #3

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.7300. Min Act: -0.1700

Data Index: 6465865 (Open Web Text)

Max Activating Token Index: 166

Text #4

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.7325. Min Act: -0.1700

Data Index: 2370583 (Open Web Text)

Max Activating Token Index: 124

Text #5

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.7204. Min Act: -0.1700

Data Index: 1332501 (Open Web Text)

Max Activating Token Index: 43

Text #6

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.7416. Min Act: -0.1700

Data Index: 2917655 (Open Web Text)

Max Activating Token Index: 656

Text #7

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.7162. Min Act: -0.1700

Data Index: 4754597 (Open Web Text)

Max Activating Token Index: 538

Text #8

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.6926. Min Act: -0.1700

Data Index: 1123607 (Open Web Text)

Max Activating Token Index: 779

Text #9

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.6905. Min Act: -0.1700

Data Index: 5299692 (Open Web Text)

Max Activating Token Index: 628

Text #10

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.6665. Min Act: -0.1699

Data Index: 1992609 (Open Web Text)

Max Activating Token Index: 164

Text #11

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.6730. Min Act: -0.1700

Data Index: 427405 (Open Web Text)

Max Activating Token Index: 180

Text #12

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.6655. Min Act: -0.1700

Data Index: 915446 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.6610. Min Act: -0.1700

Data Index: 4317203 (Open Web Text)

Max Activating Token Index: 740

Text #14

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.6628. Min Act: -0.1700

Data Index: 7691175 (Open Web Text)

Max Activating Token Index: 62

Text #15

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.6607. Min Act: -0.1700

Data Index: 2283471 (Open Web Text)

Max Activating Token Index: 985

Text #16

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.6536. Min Act: -0.1700

Data Index: 6497676 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.6649. Min Act: -0.1700

Data Index: 2269192 (Open Web Text)

Max Activating Token Index: 27

Text #18

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.6633. Min Act: -0.1700

Data Index: 8402009 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 1.7495. Min Range: -1.7495

Max Act: 1.6725. Min Act: -0.1700

Data Index: 2153529 (Open Web Text)

Max Activating Token Index: 665