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

Dataset: Open Web Text

Neuron 1418 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: 2.1602. Min Range: -2.1602

Max Act: 2.1602. Min Act: -0.1700

Data Index: 683813 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.1602. Min Range: -2.1602

Max Act: 2.0681. Min Act: -0.1700

Data Index: 5704858 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.1602. Min Range: -2.1602

Max Act: 2.0485. Min Act: -0.1700

Data Index: 4431772 (Open Web Text)

Max Activating Token Index: 891

Text #3

Max Range: 2.1602. Min Range: -2.1602

Max Act: 2.0751. Min Act: -0.1700

Data Index: 5994126 (Open Web Text)

Max Activating Token Index: 137

Text #4

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.9606. Min Act: -0.1700

Data Index: 5222859 (Open Web Text)

Max Activating Token Index: 795

Text #5

Max Range: 2.1602. Min Range: -2.1602

Max Act: 2.0467. Min Act: -0.1700

Data Index: 3898651 (Open Web Text)

Max Activating Token Index: 152

Text #6

Max Range: 2.1602. Min Range: -2.1602

Max Act: 2.0235. Min Act: -0.1700

Data Index: 2319082 (Open Web Text)

Max Activating Token Index: 635

Text #7

Max Range: 2.1602. Min Range: -2.1602

Max Act: 2.0184. Min Act: -0.1700

Data Index: 2199790 (Open Web Text)

Max Activating Token Index: 635

Text #8

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.9959. Min Act: -0.1700

Data Index: 4583819 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.9791. Min Act: -0.1700

Data Index: 628596 (Open Web Text)

Max Activating Token Index: 964

Text #10

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.9496. Min Act: -0.1700

Data Index: 8337182 (Open Web Text)

Max Activating Token Index: 794

Text #11

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.9740. Min Act: -0.1700

Data Index: 6088491 (Open Web Text)

Max Activating Token Index: 780

Text #12

Max Range: 2.1602. Min Range: -2.1602

Max Act: 2.0256. Min Act: -0.1700

Data Index: 7620682 (Open Web Text)

Max Activating Token Index: 886

Text #13

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.9747. Min Act: -0.1700

Data Index: 6758973 (Open Web Text)

Max Activating Token Index: 447

Text #14

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.9514. Min Act: -0.1700

Data Index: 1542667 (Open Web Text)

Max Activating Token Index: 877

Text #15

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.9789. Min Act: -0.1700

Data Index: 2309143 (Open Web Text)

Max Activating Token Index: 323

Text #16

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.9115. Min Act: -0.1700

Data Index: 7352138 (Open Web Text)

Max Activating Token Index: 688

Text #17

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.8849. Min Act: -0.1700

Data Index: 3194108 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.9194. Min Act: -0.1700

Data Index: 939539 (Open Web Text)

Max Activating Token Index: 597

Text #19

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.9135. Min Act: -0.1700

Data Index: 4454040 (Open Web Text)

Max Activating Token Index: 161