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

Dataset: Open Web Text

Neuron 1375 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: 1.9894. Min Range: -1.9894

Max Act: 1.9865. Min Act: -0.1700

Data Index: 1743963 (Open Web Text)

Max Activating Token Index: 276

Text #1

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.9894. Min Act: -0.1700

Data Index: 4679362 (Open Web Text)

Max Activating Token Index: 888

Text #2

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.9737. Min Act: -0.1700

Data Index: 4152466 (Open Web Text)

Max Activating Token Index: 41

Text #3

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.9835. Min Act: -0.1700

Data Index: 4318718 (Open Web Text)

Max Activating Token Index: 659

Text #4

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.9648. Min Act: -0.1700

Data Index: 1307399 (Open Web Text)

Max Activating Token Index: 94

Text #5

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.9647. Min Act: -0.1700

Data Index: 8536315 (Open Web Text)

Max Activating Token Index: 946

Text #6

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.9221. Min Act: -0.1700

Data Index: 5924804 (Open Web Text)

Max Activating Token Index: 926

Text #7

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.9151. Min Act: -0.1700

Data Index: 750046 (Open Web Text)

Max Activating Token Index: 465

Text #8

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.9062. Min Act: -0.1698

Data Index: 2675571 (Open Web Text)

Max Activating Token Index: 771

Text #9

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.9012. Min Act: -0.1700

Data Index: 1902552 (Open Web Text)

Max Activating Token Index: 196

Text #10

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8797. Min Act: -0.1700

Data Index: 1648166 (Open Web Text)

Max Activating Token Index: 570

Text #11

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8970. Min Act: -0.1700

Data Index: 1363185 (Open Web Text)

Max Activating Token Index: 942

Text #12

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8921. Min Act: -0.1700

Data Index: 761859 (Open Web Text)

Max Activating Token Index: 644

Text #13

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8874. Min Act: -0.1700

Data Index: 6392580 (Open Web Text)

Max Activating Token Index: 180

Text #14

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8887. Min Act: -0.1700

Data Index: 5093471 (Open Web Text)

Max Activating Token Index: 509

Text #15

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8973. Min Act: -0.1700

Data Index: 7635826 (Open Web Text)

Max Activating Token Index: 624

Text #16

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8784. Min Act: -0.1700

Data Index: 8323639 (Open Web Text)

Max Activating Token Index: 965

Text #17

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8765. Min Act: -0.1700

Data Index: 4880707 (Open Web Text)

Max Activating Token Index: 70

Text #18

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8668. Min Act: -0.1700

Data Index: 720615 (Open Web Text)

Max Activating Token Index: 506

Text #19

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8900. Min Act: -0.1700

Data Index: 942226 (Open Web Text)

Max Activating Token Index: 467