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

Dataset: Open Web Text

Neuron 2568 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: 3.1529. Min Range: -3.1529

Max Act: 3.1529. Min Act: -0.1700

Data Index: 3843615 (Open Web Text)

Max Activating Token Index: 175

Text #1

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.0953. Min Act: -0.1700

Data Index: 70385 (Open Web Text)

Max Activating Token Index: 301

Text #2

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.0671. Min Act: -0.1700

Data Index: 3547427 (Open Web Text)

Max Activating Token Index: 606

Text #3

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.0472. Min Act: -0.1700

Data Index: 5180688 (Open Web Text)

Max Activating Token Index: 422

Text #4

Max Range: 3.1529. Min Range: -3.1529

Max Act: 3.0103. Min Act: -0.1700

Data Index: 5416289 (Open Web Text)

Max Activating Token Index: 819

Text #5

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9908. Min Act: -0.1700

Data Index: 7200399 (Open Web Text)

Max Activating Token Index: 363

Text #6

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9887. Min Act: -0.1700

Data Index: 8693239 (Open Web Text)

Max Activating Token Index: 899

Text #7

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9994. Min Act: -0.1700

Data Index: 6293731 (Open Web Text)

Max Activating Token Index: 632

Text #8

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9857. Min Act: -0.1700

Data Index: 3843611 (Open Web Text)

Max Activating Token Index: 603

Text #9

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9695. Min Act: -0.1700

Data Index: 52973 (Open Web Text)

Max Activating Token Index: 815

Text #10

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9606. Min Act: -0.1700

Data Index: 97487 (Open Web Text)

Max Activating Token Index: 360

Text #11

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9626. Min Act: -0.1700

Data Index: 7700749 (Open Web Text)

Max Activating Token Index: 714

Text #12

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9469. Min Act: -0.1700

Data Index: 2161551 (Open Web Text)

Max Activating Token Index: 999

Text #13

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9633. Min Act: -0.1700

Data Index: 1429589 (Open Web Text)

Max Activating Token Index: 206

Text #14

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9526. Min Act: -0.1700

Data Index: 4315803 (Open Web Text)

Max Activating Token Index: 163

Text #15

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9520. Min Act: -0.1700

Data Index: 6974565 (Open Web Text)

Max Activating Token Index: 735

Text #16

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9392. Min Act: -0.1700

Data Index: 611156 (Open Web Text)

Max Activating Token Index: 393

Text #17

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9501. Min Act: -0.1700

Data Index: 7392946 (Open Web Text)

Max Activating Token Index: 1020

Text #18

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9424. Min Act: -0.1700

Data Index: 611157 (Open Web Text)

Max Activating Token Index: 145

Text #19

Max Range: 3.1529. Min Range: -3.1529

Max Act: 2.9360. Min Act: -0.1700

Data Index: 7541017 (Open Web Text)

Max Activating Token Index: 689