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

Dataset: Open Web Text

Neuron 424 in Layer 0

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: 3.3206. Min Range: -3.3206

Max Act: 3.3206. Min Act: -0.1700

Data Index: 2548302 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.2534. Min Act: -0.1700

Data Index: 2070304 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.2444. Min Act: -0.1700

Data Index: 2508247 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.2173. Min Act: -0.1700

Data Index: 2954177 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.2140. Min Act: -0.1700

Data Index: 8518709 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.2085. Min Act: -0.1700

Data Index: 1623833 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.1978. Min Act: -0.1700

Data Index: 7581650 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.1812. Min Act: -0.1700

Data Index: 5405903 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.1935. Min Act: -0.1700

Data Index: 4929829 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.1697. Min Act: -0.1700

Data Index: 119332 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.1764. Min Act: -0.1700

Data Index: 5881272 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.1744. Min Act: -0.1700

Data Index: 1762812 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.1805. Min Act: -0.1700

Data Index: 1124419 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.1634. Min Act: -0.1700

Data Index: 686034 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.1623. Min Act: -0.1700

Data Index: 1099230 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.1616. Min Act: -0.1700

Data Index: 4491465 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.1336. Min Act: -0.1700

Data Index: 463013 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.1386. Min Act: -0.1700

Data Index: 1681671 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.1433. Min Act: -0.1700

Data Index: 550587 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.3206. Min Range: -3.3206

Max Act: 3.1480. Min Act: -0.1700

Data Index: 7330903 (Open Web Text)

Max Activating Token Index: 7