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

Dataset: Open Web Text

Neuron 123 in Layer 0

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: 3.2609. Min Range: -3.2609

Max Act: 3.2609. Min Act: -0.1700

Data Index: 8693691 (Open Web Text)

Max Activating Token Index: 30

Text #1

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.2390. Min Act: -0.1700

Data Index: 4830313 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.2183. Min Act: -0.1700

Data Index: 2127692 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1865. Min Act: -0.1700

Data Index: 2978420 (Open Web Text)

Max Activating Token Index: 1020

Text #4

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1856. Min Act: -0.1700

Data Index: 164118 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1877. Min Act: -0.1700

Data Index: 3590094 (Open Web Text)

Max Activating Token Index: 23

Text #6

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1832. Min Act: -0.1700

Data Index: 8103595 (Open Web Text)

Max Activating Token Index: 32

Text #7

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1899. Min Act: -0.1700

Data Index: 8297708 (Open Web Text)

Max Activating Token Index: 76

Text #8

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1926. Min Act: -0.1700

Data Index: 4170228 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1861. Min Act: -0.1700

Data Index: 2385117 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1643. Min Act: -0.1700

Data Index: 5634427 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1621. Min Act: -0.1700

Data Index: 6735225 (Open Web Text)

Max Activating Token Index: 506

Text #12

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1586. Min Act: -0.1700

Data Index: 4465178 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1656. Min Act: -0.1700

Data Index: 3625479 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1705. Min Act: -0.1700

Data Index: 3556354 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1690. Min Act: -0.1700

Data Index: 6830185 (Open Web Text)

Max Activating Token Index: 363

Text #16

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1569. Min Act: -0.1700

Data Index: 5964403 (Open Web Text)

Max Activating Token Index: 41

Text #17

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1545. Min Act: -0.1700

Data Index: 6126273 (Open Web Text)

Max Activating Token Index: 81

Text #18

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1544. Min Act: -0.1700

Data Index: 6204517 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1524. Min Act: -0.1700

Data Index: 5262877 (Open Web Text)

Max Activating Token Index: 649