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

Dataset: Open Web Text

Neuron 2910 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: 4.9641. Min Range: -4.9641

Max Act: 4.9641. Min Act: -0.1700

Data Index: 4395614 (Open Web Text)

Max Activating Token Index: 660

Text #1

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.7053. Min Act: -0.1700

Data Index: 7295767 (Open Web Text)

Max Activating Token Index: 725

Text #2

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.7111. Min Act: -0.1700

Data Index: 1287837 (Open Web Text)

Max Activating Token Index: 543

Text #3

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.7138. Min Act: -0.1700

Data Index: 5202038 (Open Web Text)

Max Activating Token Index: 246

Text #4

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.6636. Min Act: -0.1700

Data Index: 7512811 (Open Web Text)

Max Activating Token Index: 821

Text #5

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.6622. Min Act: -0.1700

Data Index: 3690346 (Open Web Text)

Max Activating Token Index: 956

Text #6

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.6741. Min Act: -0.1700

Data Index: 796209 (Open Web Text)

Max Activating Token Index: 1021

Text #7

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.6953. Min Act: -0.1700

Data Index: 7471359 (Open Web Text)

Max Activating Token Index: 888

Text #8

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.6405. Min Act: -0.1700

Data Index: 2103264 (Open Web Text)

Max Activating Token Index: 876

Text #9

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.6708. Min Act: -0.1700

Data Index: 2457312 (Open Web Text)

Max Activating Token Index: 922

Text #10

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.6703. Min Act: -0.1700

Data Index: 4070659 (Open Web Text)

Max Activating Token Index: 250

Text #11

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.6100. Min Act: -0.1700

Data Index: 7224302 (Open Web Text)

Max Activating Token Index: 575

Text #12

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.6600. Min Act: -0.1700

Data Index: 8722859 (Open Web Text)

Max Activating Token Index: 514

Text #13

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.5945. Min Act: -0.1700

Data Index: 1663237 (Open Web Text)

Max Activating Token Index: 364

Text #14

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.6260. Min Act: -0.1700

Data Index: 4338856 (Open Web Text)

Max Activating Token Index: 174

Text #15

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.5976. Min Act: -0.1700

Data Index: 5358501 (Open Web Text)

Max Activating Token Index: 989

Text #16

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.5724. Min Act: -0.1700

Data Index: 5579587 (Open Web Text)

Max Activating Token Index: 46

Text #17

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.5789. Min Act: -0.1700

Data Index: 3667904 (Open Web Text)

Max Activating Token Index: 288

Text #18

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.5737. Min Act: -0.1700

Data Index: 6091328 (Open Web Text)

Max Activating Token Index: 875

Text #19

Max Range: 4.9641. Min Range: -4.9641

Max Act: 4.5904. Min Act: -0.1700

Data Index: 7018453 (Open Web Text)

Max Activating Token Index: 8