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

Dataset: Open Web Text

Neuron 255 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: 3.4433. Min Range: -3.4433

Max Act: 3.4433. Min Act: -0.1700

Data Index: 4593372 (Open Web Text)

Max Activating Token Index: 987

Text #1

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.3583. Min Act: -0.1700

Data Index: 2310690 (Open Web Text)

Max Activating Token Index: 351

Text #2

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.2928. Min Act: -0.1700

Data Index: 6770076 (Open Web Text)

Max Activating Token Index: 499

Text #3

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.2854. Min Act: -0.1700

Data Index: 6965728 (Open Web Text)

Max Activating Token Index: 466

Text #4

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.2493. Min Act: -0.1700

Data Index: 36881 (Open Web Text)

Max Activating Token Index: 771

Text #5

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.2582. Min Act: -0.1700

Data Index: 2762904 (Open Web Text)

Max Activating Token Index: 214

Text #6

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.2399. Min Act: -0.1700

Data Index: 4463202 (Open Web Text)

Max Activating Token Index: 83

Text #7

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.2365. Min Act: -0.1700

Data Index: 2519052 (Open Web Text)

Max Activating Token Index: 200

Text #8

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.2136. Min Act: -0.1700

Data Index: 6754026 (Open Web Text)

Max Activating Token Index: 342

Text #9

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.1922. Min Act: -0.1700

Data Index: 2687774 (Open Web Text)

Max Activating Token Index: 79

Text #10

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.1743. Min Act: -0.1700

Data Index: 2313032 (Open Web Text)

Max Activating Token Index: 461

Text #11

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.1780. Min Act: -0.1700

Data Index: 7688438 (Open Web Text)

Max Activating Token Index: 73

Text #12

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.1610. Min Act: -0.1700

Data Index: 7669312 (Open Web Text)

Max Activating Token Index: 109

Text #13

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.1724. Min Act: -0.1700

Data Index: 4334451 (Open Web Text)

Max Activating Token Index: 539

Text #14

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.1663. Min Act: -0.1700

Data Index: 7500305 (Open Web Text)

Max Activating Token Index: 522

Text #15

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.1629. Min Act: -0.1700

Data Index: 8181108 (Open Web Text)

Max Activating Token Index: 125

Text #16

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.1539. Min Act: -0.1700

Data Index: 4505015 (Open Web Text)

Max Activating Token Index: 326

Text #17

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.1625. Min Act: -0.1700

Data Index: 355885 (Open Web Text)

Max Activating Token Index: 49

Text #18

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.1663. Min Act: -0.1700

Data Index: 6142335 (Open Web Text)

Max Activating Token Index: 66

Text #19

Max Range: 3.4433. Min Range: -3.4433

Max Act: 3.1889. Min Act: -0.1700

Data Index: 5775643 (Open Web Text)

Max Activating Token Index: 668