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

Dataset: Open Web Text

Neuron 1996 in Layer 6

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: 5.5523. Min Range: -5.5523

Max Act: 5.5523. Min Act: -0.1700

Data Index: 7204811 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.2279. Min Act: -0.1700

Data Index: 8190898 (Open Web Text)

Max Activating Token Index: 519

Text #2

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.2541. Min Act: -0.1700

Data Index: 6715506 (Open Web Text)

Max Activating Token Index: 915

Text #3

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.2449. Min Act: -0.1700

Data Index: 1933309 (Open Web Text)

Max Activating Token Index: 502

Text #4

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.2551. Min Act: -0.1700

Data Index: 8288937 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.2417. Min Act: -0.1700

Data Index: 718644 (Open Web Text)

Max Activating Token Index: 111

Text #6

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.1922. Min Act: -0.1700

Data Index: 7045573 (Open Web Text)

Max Activating Token Index: 106

Text #7

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.1777. Min Act: -0.1700

Data Index: 1933308 (Open Web Text)

Max Activating Token Index: 437

Text #8

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.2054. Min Act: -0.1700

Data Index: 1086972 (Open Web Text)

Max Activating Token Index: 929

Text #9

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.1973. Min Act: -0.1700

Data Index: 7668674 (Open Web Text)

Max Activating Token Index: 508

Text #10

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.1344. Min Act: -0.1700

Data Index: 2678358 (Open Web Text)

Max Activating Token Index: 388

Text #11

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.1434. Min Act: -0.1700

Data Index: 8329032 (Open Web Text)

Max Activating Token Index: 860

Text #12

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.1391. Min Act: -0.1700

Data Index: 3964950 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.1540. Min Act: -0.1700

Data Index: 6648315 (Open Web Text)

Max Activating Token Index: 620

Text #14

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.1539. Min Act: -0.1700

Data Index: 2723356 (Open Web Text)

Max Activating Token Index: 529

Text #15

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.1270. Min Act: -0.1700

Data Index: 1957472 (Open Web Text)

Max Activating Token Index: 945

Text #16

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.1452. Min Act: -0.1700

Data Index: 3956766 (Open Web Text)

Max Activating Token Index: 18

Text #17

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.1242. Min Act: -0.1700

Data Index: 6288227 (Open Web Text)

Max Activating Token Index: 962

Text #18

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.1151. Min Act: -0.1700

Data Index: 3762424 (Open Web Text)

Max Activating Token Index: 846

Text #19

Max Range: 5.5523. Min Range: -5.5523

Max Act: 5.1091. Min Act: -0.1700

Data Index: 5027123 (Open Web Text)

Max Activating Token Index: 299