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

Dataset: Open Web Text

Neuron 920 in Layer 5

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: 3.1578. Min Range: -3.1578

Max Act: 3.1578. Min Act: -0.1700

Data Index: 3218907 (Open Web Text)

Max Activating Token Index: 219

Text #1

Max Range: 3.1578. Min Range: -3.1578

Max Act: 3.1576. Min Act: -0.1700

Data Index: 7027870 (Open Web Text)

Max Activating Token Index: 233

Text #2

Max Range: 3.1578. Min Range: -3.1578

Max Act: 3.1494. Min Act: -0.1700

Data Index: 6567771 (Open Web Text)

Max Activating Token Index: 981

Text #3

Max Range: 3.1578. Min Range: -3.1578

Max Act: 3.1161. Min Act: -0.1700

Data Index: 6330995 (Open Web Text)

Max Activating Token Index: 696

Text #4

Max Range: 3.1578. Min Range: -3.1578

Max Act: 3.0657. Min Act: -0.1700

Data Index: 7723031 (Open Web Text)

Max Activating Token Index: 876

Text #5

Max Range: 3.1578. Min Range: -3.1578

Max Act: 3.0477. Min Act: -0.1700

Data Index: 3042510 (Open Web Text)

Max Activating Token Index: 514

Text #6

Max Range: 3.1578. Min Range: -3.1578

Max Act: 3.0371. Min Act: -0.1700

Data Index: 5105972 (Open Web Text)

Max Activating Token Index: 847

Text #7

Max Range: 3.1578. Min Range: -3.1578

Max Act: 3.0207. Min Act: -0.1700

Data Index: 1748415 (Open Web Text)

Max Activating Token Index: 400

Text #8

Max Range: 3.1578. Min Range: -3.1578

Max Act: 3.0281. Min Act: -0.1700

Data Index: 965773 (Open Web Text)

Max Activating Token Index: 177

Text #9

Max Range: 3.1578. Min Range: -3.1578

Max Act: 3.0181. Min Act: -0.1700

Data Index: 5489351 (Open Web Text)

Max Activating Token Index: 678

Text #10

Max Range: 3.1578. Min Range: -3.1578

Max Act: 3.0235. Min Act: -0.1700

Data Index: 1690648 (Open Web Text)

Max Activating Token Index: 736

Text #11

Max Range: 3.1578. Min Range: -3.1578

Max Act: 2.9963. Min Act: -0.1700

Data Index: 838812 (Open Web Text)

Max Activating Token Index: 72

Text #12

Max Range: 3.1578. Min Range: -3.1578

Max Act: 2.9919. Min Act: -0.1700

Data Index: 1719507 (Open Web Text)

Max Activating Token Index: 992

Text #13

Max Range: 3.1578. Min Range: -3.1578

Max Act: 2.9908. Min Act: -0.1700

Data Index: 5398730 (Open Web Text)

Max Activating Token Index: 872

Text #14

Max Range: 3.1578. Min Range: -3.1578

Max Act: 2.9883. Min Act: -0.1700

Data Index: 1987669 (Open Web Text)

Max Activating Token Index: 1012

Text #15

Max Range: 3.1578. Min Range: -3.1578

Max Act: 2.9913. Min Act: -0.1700

Data Index: 2129856 (Open Web Text)

Max Activating Token Index: 331

Text #16

Max Range: 3.1578. Min Range: -3.1578

Max Act: 2.9809. Min Act: -0.1700

Data Index: 8459154 (Open Web Text)

Max Activating Token Index: 819

Text #17

Max Range: 3.1578. Min Range: -3.1578

Max Act: 2.9728. Min Act: -0.1700

Data Index: 507035 (Open Web Text)

Max Activating Token Index: 87

Text #18

Max Range: 3.1578. Min Range: -3.1578

Max Act: 2.9789. Min Act: -0.1700

Data Index: 1883069 (Open Web Text)

Max Activating Token Index: 580

Text #19

Max Range: 3.1578. Min Range: -3.1578

Max Act: 2.9668. Min Act: -0.1700

Data Index: 105340 (Open Web Text)

Max Activating Token Index: 752