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

Dataset: Open Web Text

Neuron 552 in Layer 4

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: 4.8802. Min Range: -4.8802

Max Act: 4.8802. Min Act: -0.1700

Data Index: 4695535 (Open Web Text)

Max Activating Token Index: 526

Text #1

Max Range: 4.8802. Min Range: -4.8802

Max Act: 4.4890. Min Act: -0.1700

Data Index: 4471160 (Open Web Text)

Max Activating Token Index: 245

Text #2

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.9253. Min Act: -0.1700

Data Index: 3078367 (Open Web Text)

Max Activating Token Index: 168

Text #3

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.9495. Min Act: -0.1700

Data Index: 370216 (Open Web Text)

Max Activating Token Index: 440

Text #4

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.9282. Min Act: -0.1700

Data Index: 8731783 (Open Web Text)

Max Activating Token Index: 360

Text #5

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.9447. Min Act: -0.1700

Data Index: 7832666 (Open Web Text)

Max Activating Token Index: 983

Text #6

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.9128. Min Act: -0.1700

Data Index: 4088165 (Open Web Text)

Max Activating Token Index: 342

Text #7

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.8879. Min Act: -0.1700

Data Index: 1731285 (Open Web Text)

Max Activating Token Index: 299

Text #8

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.8693. Min Act: -0.1700

Data Index: 8513506 (Open Web Text)

Max Activating Token Index: 195

Text #9

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.9038. Min Act: -0.1700

Data Index: 6431710 (Open Web Text)

Max Activating Token Index: 383

Text #10

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.9050. Min Act: -0.1700

Data Index: 3806719 (Open Web Text)

Max Activating Token Index: 440

Text #11

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.8902. Min Act: -0.1700

Data Index: 1180455 (Open Web Text)

Max Activating Token Index: 262

Text #12

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.8446. Min Act: -0.1700

Data Index: 3429639 (Open Web Text)

Max Activating Token Index: 323

Text #13

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.8473. Min Act: -0.1700

Data Index: 951096 (Open Web Text)

Max Activating Token Index: 424

Text #14

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.8784. Min Act: -0.1700

Data Index: 956093 (Open Web Text)

Max Activating Token Index: 483

Text #15

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.8829. Min Act: -0.1700

Data Index: 7475952 (Open Web Text)

Max Activating Token Index: 118

Text #16

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.8531. Min Act: -0.1700

Data Index: 7641618 (Open Web Text)

Max Activating Token Index: 663

Text #17

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.8563. Min Act: -0.1700

Data Index: 4049128 (Open Web Text)

Max Activating Token Index: 635

Text #18

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.8814. Min Act: -0.1700

Data Index: 5444050 (Open Web Text)

Max Activating Token Index: 995

Text #19

Max Range: 4.8802. Min Range: -4.8802

Max Act: 3.8468. Min Act: -0.1700

Data Index: 1470332 (Open Web Text)

Max Activating Token Index: 866