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

Dataset: Open Web Text

Neuron 2922 in Layer 1

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: 5.5727. Min Range: -5.5727

Max Act: 5.5727. Min Act: -0.1700

Data Index: 2774700 (Open Web Text)

Max Activating Token Index: 952

Text #1

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.4627. Min Act: -0.1700

Data Index: 5440460 (Open Web Text)

Max Activating Token Index: 186

Text #2

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.4408. Min Act: -0.1700

Data Index: 1901279 (Open Web Text)

Max Activating Token Index: 106

Text #3

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.4400. Min Act: -0.1700

Data Index: 3653934 (Open Web Text)

Max Activating Token Index: 467

Text #4

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.4393. Min Act: -0.1700

Data Index: 6163204 (Open Web Text)

Max Activating Token Index: 369

Text #5

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.4342. Min Act: -0.1700

Data Index: 8620868 (Open Web Text)

Max Activating Token Index: 501

Text #6

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.4051. Min Act: -0.1700

Data Index: 6642938 (Open Web Text)

Max Activating Token Index: 553

Text #7

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.4105. Min Act: -0.1700

Data Index: 4622503 (Open Web Text)

Max Activating Token Index: 611

Text #8

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.4118. Min Act: -0.1700

Data Index: 4225417 (Open Web Text)

Max Activating Token Index: 576

Text #9

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.4275. Min Act: -0.1700

Data Index: 8324808 (Open Web Text)

Max Activating Token Index: 292

Text #10

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.4316. Min Act: -0.1700

Data Index: 6284190 (Open Web Text)

Max Activating Token Index: 841

Text #11

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.3731. Min Act: -0.1700

Data Index: 7156277 (Open Web Text)

Max Activating Token Index: 767

Text #12

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.4049. Min Act: -0.1700

Data Index: 7308618 (Open Web Text)

Max Activating Token Index: 683

Text #13

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.3981. Min Act: -0.1700

Data Index: 7514596 (Open Web Text)

Max Activating Token Index: 633

Text #14

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.3716. Min Act: -0.1700

Data Index: 6055595 (Open Web Text)

Max Activating Token Index: 120

Text #15

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.3968. Min Act: -0.1700

Data Index: 2193039 (Open Web Text)

Max Activating Token Index: 98

Text #16

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.4065. Min Act: -0.1700

Data Index: 203159 (Open Web Text)

Max Activating Token Index: 574

Text #17

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.3826. Min Act: -0.1700

Data Index: 4331096 (Open Web Text)

Max Activating Token Index: 41

Text #18

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.3915. Min Act: -0.1700

Data Index: 738425 (Open Web Text)

Max Activating Token Index: 356

Text #19

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.3831. Min Act: -0.1700

Data Index: 8534433 (Open Web Text)

Max Activating Token Index: 691