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

Dataset: Open Web Text

Neuron 1245 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: 3.0662. Min Range: -3.0662

Max Act: 3.0662. Min Act: -0.1700

Data Index: 2563531 (Open Web Text)

Max Activating Token Index: 882

Text #1

Max Range: 3.0662. Min Range: -3.0662

Max Act: 3.0009. Min Act: -0.1700

Data Index: 3200745 (Open Web Text)

Max Activating Token Index: 551

Text #2

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.9423. Min Act: -0.1700

Data Index: 3886108 (Open Web Text)

Max Activating Token Index: 911

Text #3

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8882. Min Act: -0.1700

Data Index: 8044421 (Open Web Text)

Max Activating Token Index: 431

Text #4

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8419. Min Act: -0.1700

Data Index: 1812426 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8463. Min Act: -0.1700

Data Index: 940717 (Open Web Text)

Max Activating Token Index: 965

Text #6

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8666. Min Act: -0.1700

Data Index: 5592474 (Open Web Text)

Max Activating Token Index: 488

Text #7

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8448. Min Act: -0.1700

Data Index: 7870714 (Open Web Text)

Max Activating Token Index: 1011

Text #8

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8570. Min Act: -0.1700

Data Index: 6200621 (Open Web Text)

Max Activating Token Index: 199

Text #9

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8293. Min Act: -0.1700

Data Index: 8091240 (Open Web Text)

Max Activating Token Index: 394

Text #10

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8290. Min Act: -0.1700

Data Index: 3886849 (Open Web Text)

Max Activating Token Index: 935

Text #11

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8288. Min Act: -0.1700

Data Index: 8657713 (Open Web Text)

Max Activating Token Index: 506

Text #12

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8339. Min Act: -0.1700

Data Index: 4920595 (Open Web Text)

Max Activating Token Index: 1015

Text #13

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8199. Min Act: -0.1700

Data Index: 2907853 (Open Web Text)

Max Activating Token Index: 976

Text #14

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8236. Min Act: -0.1700

Data Index: 8235870 (Open Web Text)

Max Activating Token Index: 1021

Text #15

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8157. Min Act: -0.1700

Data Index: 2943834 (Open Web Text)

Max Activating Token Index: 940

Text #16

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.7998. Min Act: -0.1700

Data Index: 7491363 (Open Web Text)

Max Activating Token Index: 900

Text #17

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8101. Min Act: -0.1700

Data Index: 4683213 (Open Web Text)

Max Activating Token Index: 968

Text #18

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8165. Min Act: -0.1700

Data Index: 186030 (Open Web Text)

Max Activating Token Index: 548

Text #19

Max Range: 3.0662. Min Range: -3.0662

Max Act: 2.8330. Min Act: -0.1700

Data Index: 4762471 (Open Web Text)

Max Activating Token Index: 1011