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

Dataset: Open Web Text

Neuron 3063 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: 3.1910. Min Range: -3.1910

Max Act: 3.1910. Min Act: -0.1700

Data Index: 2775183 (Open Web Text)

Max Activating Token Index: 750

Text #1

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.1721. Min Act: -0.1700

Data Index: 666795 (Open Web Text)

Max Activating Token Index: 462

Text #2

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.1783. Min Act: -0.1700

Data Index: 1770220 (Open Web Text)

Max Activating Token Index: 177

Text #3

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.1469. Min Act: -0.1700

Data Index: 2500699 (Open Web Text)

Max Activating Token Index: 955

Text #4

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.1493. Min Act: -0.1700

Data Index: 6074020 (Open Web Text)

Max Activating Token Index: 251

Text #5

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.1213. Min Act: -0.1700

Data Index: 7416277 (Open Web Text)

Max Activating Token Index: 349

Text #6

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.1298. Min Act: -0.1700

Data Index: 186738 (Open Web Text)

Max Activating Token Index: 174

Text #7

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.1118. Min Act: -0.1700

Data Index: 904982 (Open Web Text)

Max Activating Token Index: 357

Text #8

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.0579. Min Act: -0.1700

Data Index: 7209501 (Open Web Text)

Max Activating Token Index: 252

Text #9

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.0318. Min Act: -0.1700

Data Index: 4659855 (Open Web Text)

Max Activating Token Index: 514

Text #10

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.0236. Min Act: -0.1700

Data Index: 2249481 (Open Web Text)

Max Activating Token Index: 653

Text #11

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.0508. Min Act: -0.1700

Data Index: 2695553 (Open Web Text)

Max Activating Token Index: 711

Text #12

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.0522. Min Act: -0.1700

Data Index: 922563 (Open Web Text)

Max Activating Token Index: 604

Text #13

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.0050. Min Act: -0.1700

Data Index: 8359747 (Open Web Text)

Max Activating Token Index: 91

Text #14

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.9923. Min Act: -0.1700

Data Index: 8736060 (Open Web Text)

Max Activating Token Index: 969

Text #15

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.9880. Min Act: -0.1700

Data Index: 650555 (Open Web Text)

Max Activating Token Index: 604

Text #16

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.9963. Min Act: -0.1700

Data Index: 8012596 (Open Web Text)

Max Activating Token Index: 542

Text #17

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.9649. Min Act: -0.1700

Data Index: 8572493 (Open Web Text)

Max Activating Token Index: 233

Text #18

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.9586. Min Act: -0.1700

Data Index: 6943257 (Open Web Text)

Max Activating Token Index: 754

Text #19

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.9862. Min Act: -0.1700

Data Index: 1492761 (Open Web Text)

Max Activating Token Index: 144