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

Dataset: Open Web Text

Neuron 2601 in Layer 6

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: 4.0910. Min Range: -4.0910

Max Act: 4.0910. Min Act: -0.1700

Data Index: 7791824 (Open Web Text)

Max Activating Token Index: 945

Text #1

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.9570. Min Act: -0.1700

Data Index: 1198702 (Open Web Text)

Max Activating Token Index: 433

Text #2

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.9220. Min Act: -0.1700

Data Index: 5523049 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.9336. Min Act: -0.1700

Data Index: 7896531 (Open Web Text)

Max Activating Token Index: 881

Text #4

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.8989. Min Act: -0.1700

Data Index: 2828513 (Open Web Text)

Max Activating Token Index: 596

Text #5

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.9196. Min Act: -0.1700

Data Index: 3815479 (Open Web Text)

Max Activating Token Index: 422

Text #6

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.8930. Min Act: -0.1700

Data Index: 6625066 (Open Web Text)

Max Activating Token Index: 54

Text #7

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.8845. Min Act: -0.1700

Data Index: 2550279 (Open Web Text)

Max Activating Token Index: 684

Text #8

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.8595. Min Act: -0.1700

Data Index: 2013413 (Open Web Text)

Max Activating Token Index: 697

Text #9

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.7991. Min Act: -0.1700

Data Index: 2223220 (Open Web Text)

Max Activating Token Index: 691

Text #10

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.8555. Min Act: -0.1700

Data Index: 5611497 (Open Web Text)

Max Activating Token Index: 265

Text #11

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.8496. Min Act: -0.1700

Data Index: 814075 (Open Web Text)

Max Activating Token Index: 731

Text #12

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.7953. Min Act: -0.1700

Data Index: 3740443 (Open Web Text)

Max Activating Token Index: 897

Text #13

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.7935. Min Act: -0.1700

Data Index: 5991495 (Open Web Text)

Max Activating Token Index: 920

Text #14

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.8115. Min Act: -0.1700

Data Index: 5650969 (Open Web Text)

Max Activating Token Index: 381

Text #15

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.8021. Min Act: -0.1700

Data Index: 7931921 (Open Web Text)

Max Activating Token Index: 861

Text #16

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.8312. Min Act: -0.1700

Data Index: 4165464 (Open Web Text)

Max Activating Token Index: 401

Text #17

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.7848. Min Act: -0.1700

Data Index: 3211533 (Open Web Text)

Max Activating Token Index: 1009

Text #18

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.8018. Min Act: -0.1700

Data Index: 5615840 (Open Web Text)

Max Activating Token Index: 124

Text #19

Max Range: 4.0910. Min Range: -4.0910

Max Act: 3.8310. Min Act: -0.1700

Data Index: 6253749 (Open Web Text)

Max Activating Token Index: 424