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

Dataset: Open Web Text

Neuron 2487 in Layer 2

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: 3.0924. Min Range: -3.0924

Max Act: 3.0924. Min Act: -0.1700

Data Index: 5178105 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.9528. Min Act: -0.1700

Data Index: 608709 (Open Web Text)

Max Activating Token Index: 953

Text #2

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.9957. Min Act: -0.1700

Data Index: 2252889 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.8558. Min Act: -0.1700

Data Index: 1112814 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.8504. Min Act: -0.1700

Data Index: 7465541 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.8212. Min Act: -0.1700

Data Index: 5377285 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.8046. Min Act: -0.1700

Data Index: 1334295 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.7536. Min Act: -0.1700

Data Index: 1511095 (Open Web Text)

Max Activating Token Index: 799

Text #8

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.7071. Min Act: -0.1700

Data Index: 3221215 (Open Web Text)

Max Activating Token Index: 285

Text #9

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.7200. Min Act: -0.1700

Data Index: 3270837 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.6659. Min Act: -0.1700

Data Index: 7937982 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.7055. Min Act: -0.1700

Data Index: 1378592 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.7082. Min Act: -0.1700

Data Index: 1878421 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.6703. Min Act: -0.1700

Data Index: 1922486 (Open Web Text)

Max Activating Token Index: 174

Text #14

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.6629. Min Act: -0.1700

Data Index: 6580267 (Open Web Text)

Max Activating Token Index: 505

Text #15

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.6567. Min Act: -0.1700

Data Index: 7492433 (Open Web Text)

Max Activating Token Index: 379

Text #16

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.6378. Min Act: -0.1700

Data Index: 1928814 (Open Web Text)

Max Activating Token Index: 446

Text #17

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.6404. Min Act: -0.1700

Data Index: 5694262 (Open Web Text)

Max Activating Token Index: 767

Text #18

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.6393. Min Act: -0.1700

Data Index: 930016 (Open Web Text)

Max Activating Token Index: 767

Text #19

Max Range: 3.0924. Min Range: -3.0924

Max Act: 2.6069. Min Act: -0.1700

Data Index: 4370612 (Open Web Text)

Max Activating Token Index: 1023