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

Dataset: Open Web Text

Neuron 1483 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: 3.9420. Min Range: -3.9420

Max Act: 3.9318. Min Act: -0.1700

Data Index: 1994029 (Open Web Text)

Max Activating Token Index: 379

Text #1

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.9420. Min Act: -0.1700

Data Index: 4378977 (Open Web Text)

Max Activating Token Index: 988

Text #2

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.8310. Min Act: -0.1700

Data Index: 8775817 (Open Web Text)

Max Activating Token Index: 742

Text #3

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.8002. Min Act: -0.1700

Data Index: 8369851 (Open Web Text)

Max Activating Token Index: 955

Text #4

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.7715. Min Act: -0.1700

Data Index: 631182 (Open Web Text)

Max Activating Token Index: 771

Text #5

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.7585. Min Act: -0.1700

Data Index: 3593221 (Open Web Text)

Max Activating Token Index: 769

Text #6

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.7453. Min Act: -0.1700

Data Index: 4591150 (Open Web Text)

Max Activating Token Index: 703

Text #7

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.7787. Min Act: -0.1700

Data Index: 470639 (Open Web Text)

Max Activating Token Index: 183

Text #8

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.7234. Min Act: -0.1700

Data Index: 2559778 (Open Web Text)

Max Activating Token Index: 586

Text #9

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.7266. Min Act: -0.1700

Data Index: 7468643 (Open Web Text)

Max Activating Token Index: 86

Text #10

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.7273. Min Act: -0.1700

Data Index: 462142 (Open Web Text)

Max Activating Token Index: 954

Text #11

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.7407. Min Act: -0.1700

Data Index: 4889490 (Open Web Text)

Max Activating Token Index: 776

Text #12

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.7304. Min Act: -0.1700

Data Index: 3875301 (Open Web Text)

Max Activating Token Index: 766

Text #13

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.7599. Min Act: -0.1700

Data Index: 5032596 (Open Web Text)

Max Activating Token Index: 375

Text #14

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.6872. Min Act: -0.1700

Data Index: 1134866 (Open Web Text)

Max Activating Token Index: 428

Text #15

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.6993. Min Act: -0.1700

Data Index: 2047375 (Open Web Text)

Max Activating Token Index: 879

Text #16

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.7198. Min Act: -0.1700

Data Index: 8308967 (Open Web Text)

Max Activating Token Index: 105

Text #17

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.7060. Min Act: -0.1700

Data Index: 7979851 (Open Web Text)

Max Activating Token Index: 150

Text #18

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.7055. Min Act: -0.1700

Data Index: 4427036 (Open Web Text)

Max Activating Token Index: 39

Text #19

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.7111. Min Act: -0.1700

Data Index: 3054368 (Open Web Text)

Max Activating Token Index: 214