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

Dataset: Open Web Text

Neuron 607 in Layer 4

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: 3.0062. Min Range: -3.0062

Max Act: 3.0062. Min Act: -0.1700

Data Index: 6157737 (Open Web Text)

Max Activating Token Index: 974

Text #1

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.9753. Min Act: -0.1700

Data Index: 1508544 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.9636. Min Act: -0.1700

Data Index: 730863 (Open Web Text)

Max Activating Token Index: 968

Text #3

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.9307. Min Act: -0.1700

Data Index: 1293139 (Open Web Text)

Max Activating Token Index: 519

Text #4

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.9487. Min Act: -0.1700

Data Index: 692447 (Open Web Text)

Max Activating Token Index: 644

Text #5

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.9194. Min Act: -0.1700

Data Index: 6630207 (Open Web Text)

Max Activating Token Index: 347

Text #6

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.9091. Min Act: -0.1700

Data Index: 3959757 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.8587. Min Act: -0.1700

Data Index: 3505242 (Open Web Text)

Max Activating Token Index: 577

Text #8

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.9319. Min Act: -0.1700

Data Index: 6356442 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.8951. Min Act: -0.1700

Data Index: 6010723 (Open Web Text)

Max Activating Token Index: 736

Text #10

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.8803. Min Act: -0.1700

Data Index: 7875443 (Open Web Text)

Max Activating Token Index: 719

Text #11

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.8809. Min Act: -0.1700

Data Index: 6428296 (Open Web Text)

Max Activating Token Index: 332

Text #12

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.9084. Min Act: -0.1700

Data Index: 1579605 (Open Web Text)

Max Activating Token Index: 343

Text #13

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.8947. Min Act: -0.1700

Data Index: 2874151 (Open Web Text)

Max Activating Token Index: 123

Text #14

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.9054. Min Act: -0.1700

Data Index: 2657919 (Open Web Text)

Max Activating Token Index: 500

Text #15

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.8864. Min Act: -0.1700

Data Index: 4445552 (Open Web Text)

Max Activating Token Index: 827

Text #16

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.9055. Min Act: -0.1700

Data Index: 6763071 (Open Web Text)

Max Activating Token Index: 295

Text #17

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.9041. Min Act: -0.1700

Data Index: 2425996 (Open Web Text)

Max Activating Token Index: 149

Text #18

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.8565. Min Act: -0.1700

Data Index: 5316226 (Open Web Text)

Max Activating Token Index: 503

Text #19

Max Range: 3.0062. Min Range: -3.0062

Max Act: 2.8876. Min Act: -0.1700

Data Index: 1729177 (Open Web Text)

Max Activating Token Index: 767