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

Dataset: Open Web Text

Neuron 1677 in Layer 3

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: 4.1045. Min Range: -4.1045

Max Act: 4.1045. Min Act: -0.1700

Data Index: 7293080 (Open Web Text)

Max Activating Token Index: 540

Text #1

Max Range: 4.1045. Min Range: -4.1045

Max Act: 4.0141. Min Act: -0.1700

Data Index: 2335248 (Open Web Text)

Max Activating Token Index: 909

Text #2

Max Range: 4.1045. Min Range: -4.1045

Max Act: 4.0926. Min Act: -0.1700

Data Index: 6909826 (Open Web Text)

Max Activating Token Index: 996

Text #3

Max Range: 4.1045. Min Range: -4.1045

Max Act: 3.9979. Min Act: -0.1700

Data Index: 5617671 (Open Web Text)

Max Activating Token Index: 890

Text #4

Max Range: 4.1045. Min Range: -4.1045

Max Act: 4.0573. Min Act: -0.1700

Data Index: 4622243 (Open Web Text)

Max Activating Token Index: 862

Text #5

Max Range: 4.1045. Min Range: -4.1045

Max Act: 4.0577. Min Act: -0.1700

Data Index: 3066699 (Open Web Text)

Max Activating Token Index: 838

Text #6

Max Range: 4.1045. Min Range: -4.1045

Max Act: 4.0222. Min Act: -0.1700

Data Index: 3544564 (Open Web Text)

Max Activating Token Index: 933

Text #7

Max Range: 4.1045. Min Range: -4.1045

Max Act: 4.0047. Min Act: -0.1700

Data Index: 7941034 (Open Web Text)

Max Activating Token Index: 925

Text #8

Max Range: 4.1045. Min Range: -4.1045

Max Act: 3.9727. Min Act: -0.1700

Data Index: 8514083 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 4.1045. Min Range: -4.1045

Max Act: 4.0393. Min Act: -0.1700

Data Index: 5422874 (Open Web Text)

Max Activating Token Index: 878

Text #10

Max Range: 4.1045. Min Range: -4.1045

Max Act: 3.9601. Min Act: -0.1700

Data Index: 3014686 (Open Web Text)

Max Activating Token Index: 864

Text #11

Max Range: 4.1045. Min Range: -4.1045

Max Act: 4.0281. Min Act: -0.1700

Data Index: 5945908 (Open Web Text)

Max Activating Token Index: 965

Text #12

Max Range: 4.1045. Min Range: -4.1045

Max Act: 4.0128. Min Act: -0.1700

Data Index: 4052277 (Open Web Text)

Max Activating Token Index: 850

Text #13

Max Range: 4.1045. Min Range: -4.1045

Max Act: 3.9994. Min Act: -0.1700

Data Index: 2798530 (Open Web Text)

Max Activating Token Index: 861

Text #14

Max Range: 4.1045. Min Range: -4.1045

Max Act: 3.9434. Min Act: -0.1700

Data Index: 3837423 (Open Web Text)

Max Activating Token Index: 786

Text #15

Max Range: 4.1045. Min Range: -4.1045

Max Act: 3.9821. Min Act: -0.1700

Data Index: 1552905 (Open Web Text)

Max Activating Token Index: 746

Text #16

Max Range: 4.1045. Min Range: -4.1045

Max Act: 3.9994. Min Act: -0.1700

Data Index: 4237871 (Open Web Text)

Max Activating Token Index: 345

Text #17

Max Range: 4.1045. Min Range: -4.1045

Max Act: 3.9645. Min Act: -0.1700

Data Index: 4459477 (Open Web Text)

Max Activating Token Index: 628

Text #18

Max Range: 4.1045. Min Range: -4.1045

Max Act: 3.9341. Min Act: -0.1700

Data Index: 3163115 (Open Web Text)

Max Activating Token Index: 596

Text #19

Max Range: 4.1045. Min Range: -4.1045

Max Act: 3.9341. Min Act: -0.1700

Data Index: 3451364 (Open Web Text)

Max Activating Token Index: 745