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

Dataset: Open Web Text

Neuron 1743 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: 4.3666. Min Range: -4.3666

Max Act: 4.3666. Min Act: -0.1700

Data Index: 3480247 (Open Web Text)

Max Activating Token Index: 172

Text #1

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.3140. Min Act: -0.1700

Data Index: 8799973 (Open Web Text)

Max Activating Token Index: 671

Text #2

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.2512. Min Act: -0.1700

Data Index: 2204919 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.2520. Min Act: -0.1700

Data Index: 8516403 (Open Web Text)

Max Activating Token Index: 963

Text #4

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.2249. Min Act: -0.1700

Data Index: 7641628 (Open Web Text)

Max Activating Token Index: 870

Text #5

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.2392. Min Act: -0.1700

Data Index: 827894 (Open Web Text)

Max Activating Token Index: 42

Text #6

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.2197. Min Act: -0.1700

Data Index: 6155300 (Open Web Text)

Max Activating Token Index: 49

Text #7

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.2080. Min Act: -0.1700

Data Index: 3730965 (Open Web Text)

Max Activating Token Index: 38

Text #8

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.2213. Min Act: -0.1700

Data Index: 3480246 (Open Web Text)

Max Activating Token Index: 1002

Text #9

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.2199. Min Act: -0.1700

Data Index: 6876854 (Open Web Text)

Max Activating Token Index: 787

Text #10

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.2113. Min Act: -0.1700

Data Index: 649697 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.1879. Min Act: -0.1700

Data Index: 138200 (Open Web Text)

Max Activating Token Index: 676

Text #12

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.1675. Min Act: -0.1700

Data Index: 451862 (Open Web Text)

Max Activating Token Index: 162

Text #13

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.1353. Min Act: -0.1700

Data Index: 4132918 (Open Web Text)

Max Activating Token Index: 586

Text #14

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.1160. Min Act: -0.1700

Data Index: 2187730 (Open Web Text)

Max Activating Token Index: 803

Text #15

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.1271. Min Act: -0.1700

Data Index: 3561386 (Open Web Text)

Max Activating Token Index: 131

Text #16

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.1235. Min Act: -0.1700

Data Index: 290900 (Open Web Text)

Max Activating Token Index: 729

Text #17

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.1473. Min Act: -0.1700

Data Index: 1955265 (Open Web Text)

Max Activating Token Index: 423

Text #18

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.1114. Min Act: -0.1700

Data Index: 1711884 (Open Web Text)

Max Activating Token Index: 678

Text #19

Max Range: 4.3666. Min Range: -4.3666

Max Act: 4.1230. Min Act: -0.1700

Data Index: 3497214 (Open Web Text)

Max Activating Token Index: 336