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

Dataset: Open Web Text

Neuron 1846 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: 3.8303. Min Range: -3.8303

Max Act: 3.8303. Min Act: -0.1700

Data Index: 4844852 (Open Web Text)

Max Activating Token Index: 486

Text #1

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.8303. Min Act: -0.1700

Data Index: 6826179 (Open Web Text)

Max Activating Token Index: 272

Text #2

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7901. Min Act: -0.1700

Data Index: 4844854 (Open Web Text)

Max Activating Token Index: 436

Text #3

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7741. Min Act: -0.1700

Data Index: 1156218 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.6714. Min Act: -0.1700

Data Index: 140839 (Open Web Text)

Max Activating Token Index: 633

Text #5

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.6148. Min Act: -0.1700

Data Index: 2930925 (Open Web Text)

Max Activating Token Index: 321

Text #6

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.5857. Min Act: -0.1700

Data Index: 8757924 (Open Web Text)

Max Activating Token Index: 630

Text #7

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.5107. Min Act: -0.1700

Data Index: 8774325 (Open Web Text)

Max Activating Token Index: 586

Text #8

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.4770. Min Act: -0.1700

Data Index: 2930920 (Open Web Text)

Max Activating Token Index: 692

Text #9

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.4917. Min Act: -0.1700

Data Index: 2930929 (Open Web Text)

Max Activating Token Index: 279

Text #10

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.4632. Min Act: -0.1700

Data Index: 222296 (Open Web Text)

Max Activating Token Index: 808

Text #11

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.4617. Min Act: -0.1700

Data Index: 4538922 (Open Web Text)

Max Activating Token Index: 677

Text #12

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.4223. Min Act: -0.1700

Data Index: 2930931 (Open Web Text)

Max Activating Token Index: 568

Text #13

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.4052. Min Act: -0.1700

Data Index: 7688474 (Open Web Text)

Max Activating Token Index: 468

Text #14

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.4301. Min Act: -0.1700

Data Index: 8027064 (Open Web Text)

Max Activating Token Index: 68

Text #15

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.4006. Min Act: -0.1700

Data Index: 3121003 (Open Web Text)

Max Activating Token Index: 504

Text #16

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.3463. Min Act: -0.1700

Data Index: 5967395 (Open Web Text)

Max Activating Token Index: 321

Text #17

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.3926. Min Act: -0.1700

Data Index: 960363 (Open Web Text)

Max Activating Token Index: 94

Text #18

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.3893. Min Act: -0.1700

Data Index: 2930922 (Open Web Text)

Max Activating Token Index: 290

Text #19

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.3782. Min Act: -0.1700

Data Index: 7688473 (Open Web Text)

Max Activating Token Index: 791