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

Dataset: Open Web Text

Neuron 3011 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: 2.2585. Min Range: -2.2585

Max Act: 2.2529. Min Act: -0.1700

Data Index: 5720511 (Open Web Text)

Max Activating Token Index: 887

Text #1

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.2400. Min Act: -0.1700

Data Index: 7722182 (Open Web Text)

Max Activating Token Index: 806

Text #2

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.2540. Min Act: -0.1700

Data Index: 273354 (Open Web Text)

Max Activating Token Index: 949

Text #3

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.2585. Min Act: -0.1700

Data Index: 6750952 (Open Web Text)

Max Activating Token Index: 961

Text #4

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.2500. Min Act: -0.1700

Data Index: 1638053 (Open Web Text)

Max Activating Token Index: 887

Text #5

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.2394. Min Act: -0.1700

Data Index: 7175831 (Open Web Text)

Max Activating Token Index: 645

Text #6

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.2468. Min Act: -0.1700

Data Index: 1288226 (Open Web Text)

Max Activating Token Index: 909

Text #7

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.2345. Min Act: -0.1700

Data Index: 6200341 (Open Web Text)

Max Activating Token Index: 870

Text #8

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.2263. Min Act: -0.1700

Data Index: 6902230 (Open Web Text)

Max Activating Token Index: 910

Text #9

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.2085. Min Act: -0.1700

Data Index: 5869233 (Open Web Text)

Max Activating Token Index: 455

Text #10

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.1995. Min Act: -0.1700

Data Index: 7881068 (Open Web Text)

Max Activating Token Index: 825

Text #11

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.1828. Min Act: -0.1700

Data Index: 4326647 (Open Web Text)

Max Activating Token Index: 815

Text #12

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.1815. Min Act: -0.1700

Data Index: 8832716 (Open Web Text)

Max Activating Token Index: 464

Text #13

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.1624. Min Act: -0.1700

Data Index: 3246956 (Open Web Text)

Max Activating Token Index: 412

Text #14

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.1644. Min Act: -0.1700

Data Index: 8044335 (Open Web Text)

Max Activating Token Index: 527

Text #15

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.1637. Min Act: -0.1700

Data Index: 3254857 (Open Web Text)

Max Activating Token Index: 918

Text #16

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.1644. Min Act: -0.1700

Data Index: 7489033 (Open Web Text)

Max Activating Token Index: 734

Text #17

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.1492. Min Act: -0.1700

Data Index: 2875161 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.1569. Min Act: -0.1700

Data Index: 248433 (Open Web Text)

Max Activating Token Index: 196

Text #19

Max Range: 2.2585. Min Range: -2.2585

Max Act: 2.1497. Min Act: -0.1700

Data Index: 7014939 (Open Web Text)

Max Activating Token Index: 456