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

Dataset: Open Web Text

Neuron 2225 in Layer 0

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: 4.4913. Min Range: -4.4913

Max Act: 4.4913. Min Act: -0.1700

Data Index: 1280650 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.3768. Min Act: -0.1700

Data Index: 7090710 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.3335. Min Act: -0.1700

Data Index: 2118229 (Open Web Text)

Max Activating Token Index: 827

Text #3

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.3662. Min Act: -0.1700

Data Index: 3537358 (Open Web Text)

Max Activating Token Index: 951

Text #4

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.3192. Min Act: -0.1700

Data Index: 6167422 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.2872. Min Act: -0.1700

Data Index: 5875969 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.3176. Min Act: -0.1700

Data Index: 3764566 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.2895. Min Act: -0.1700

Data Index: 8231941 (Open Web Text)

Max Activating Token Index: 719

Text #8

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.2744. Min Act: -0.1700

Data Index: 5014310 (Open Web Text)

Max Activating Token Index: 1006

Text #9

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.2822. Min Act: -0.1700

Data Index: 3278348 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.2803. Min Act: -0.1700

Data Index: 633866 (Open Web Text)

Max Activating Token Index: 898

Text #11

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.2783. Min Act: -0.1700

Data Index: 1993616 (Open Web Text)

Max Activating Token Index: 911

Text #12

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.3020. Min Act: -0.1700

Data Index: 1992359 (Open Web Text)

Max Activating Token Index: 1018

Text #13

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.2564. Min Act: -0.1700

Data Index: 5839988 (Open Web Text)

Max Activating Token Index: 71

Text #14

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.2563. Min Act: -0.1700

Data Index: 1098841 (Open Web Text)

Max Activating Token Index: 994

Text #15

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.2379. Min Act: -0.1700

Data Index: 159667 (Open Web Text)

Max Activating Token Index: 819

Text #16

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.2545. Min Act: -0.1700

Data Index: 1843876 (Open Web Text)

Max Activating Token Index: 974

Text #17

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.2439. Min Act: -0.1700

Data Index: 1108637 (Open Web Text)

Max Activating Token Index: 980

Text #18

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.2386. Min Act: -0.1700

Data Index: 4262590 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 4.4913. Min Range: -4.4913

Max Act: 4.2261. Min Act: -0.1700

Data Index: 7441960 (Open Web Text)

Max Activating Token Index: 373