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

Dataset: Open Web Text

Neuron 27 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: 3.2926. Min Range: -3.2926

Max Act: 3.2926. Min Act: -0.1700

Data Index: 7499198 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.2746. Min Act: -0.1700

Data Index: 8820227 (Open Web Text)

Max Activating Token Index: 707

Text #2

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.1558. Min Act: -0.1700

Data Index: 2154362 (Open Web Text)

Max Activating Token Index: 311

Text #3

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.1128. Min Act: -0.1700

Data Index: 112956 (Open Web Text)

Max Activating Token Index: 320

Text #4

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.1519. Min Act: -0.1700

Data Index: 5410997 (Open Web Text)

Max Activating Token Index: 723

Text #5

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.1507. Min Act: -0.1700

Data Index: 7499199 (Open Web Text)

Max Activating Token Index: 735

Text #6

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.1073. Min Act: -0.1700

Data Index: 3121454 (Open Web Text)

Max Activating Token Index: 424

Text #7

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.1130. Min Act: -0.1700

Data Index: 4826015 (Open Web Text)

Max Activating Token Index: 553

Text #8

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.1202. Min Act: -0.1700

Data Index: 4297205 (Open Web Text)

Max Activating Token Index: 867

Text #9

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.0794. Min Act: -0.1700

Data Index: 7499200 (Open Web Text)

Max Activating Token Index: 606

Text #10

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.0932. Min Act: -0.1700

Data Index: 6052812 (Open Web Text)

Max Activating Token Index: 856

Text #11

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.0818. Min Act: -0.1700

Data Index: 2704383 (Open Web Text)

Max Activating Token Index: 268

Text #12

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.0604. Min Act: -0.1700

Data Index: 262451 (Open Web Text)

Max Activating Token Index: 763

Text #13

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.0923. Min Act: -0.1700

Data Index: 8762497 (Open Web Text)

Max Activating Token Index: 624

Text #14

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.0979. Min Act: -0.1700

Data Index: 789591 (Open Web Text)

Max Activating Token Index: 590

Text #15

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.0696. Min Act: -0.1700

Data Index: 6910417 (Open Web Text)

Max Activating Token Index: 360

Text #16

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.0613. Min Act: -0.1700

Data Index: 3744462 (Open Web Text)

Max Activating Token Index: 779

Text #17

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.0438. Min Act: -0.1700

Data Index: 4906350 (Open Web Text)

Max Activating Token Index: 244

Text #18

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.0390. Min Act: -0.1700

Data Index: 6711937 (Open Web Text)

Max Activating Token Index: 628

Text #19

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.0467. Min Act: -0.1700

Data Index: 7500905 (Open Web Text)

Max Activating Token Index: 43