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

Dataset: Open Web Text

Neuron 1172 in Layer 5

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: 4.1704. Min Range: -4.1704

Max Act: 4.1704. Min Act: -0.1700

Data Index: 8404915 (Open Web Text)

Max Activating Token Index: 362

Text #1

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.8190. Min Act: -0.1700

Data Index: 8739701 (Open Web Text)

Max Activating Token Index: 468

Text #2

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.8339. Min Act: -0.1700

Data Index: 1080978 (Open Web Text)

Max Activating Token Index: 683

Text #3

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.8607. Min Act: -0.1700

Data Index: 3928317 (Open Web Text)

Max Activating Token Index: 867

Text #4

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.8123. Min Act: -0.1700

Data Index: 4240906 (Open Web Text)

Max Activating Token Index: 891

Text #5

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.8409. Min Act: -0.1700

Data Index: 424514 (Open Web Text)

Max Activating Token Index: 490

Text #6

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.8011. Min Act: -0.1700

Data Index: 3043728 (Open Web Text)

Max Activating Token Index: 559

Text #7

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.8251. Min Act: -0.1700

Data Index: 3321734 (Open Web Text)

Max Activating Token Index: 424

Text #8

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.8133. Min Act: -0.1700

Data Index: 4662009 (Open Web Text)

Max Activating Token Index: 714

Text #9

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.8154. Min Act: -0.1700

Data Index: 2500706 (Open Web Text)

Max Activating Token Index: 338

Text #10

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.7887. Min Act: -0.1700

Data Index: 7283218 (Open Web Text)

Max Activating Token Index: 435

Text #11

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.7744. Min Act: -0.1700

Data Index: 5308294 (Open Web Text)

Max Activating Token Index: 470

Text #12

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.7847. Min Act: -0.1700

Data Index: 2405073 (Open Web Text)

Max Activating Token Index: 347

Text #13

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.7794. Min Act: -0.1700

Data Index: 366707 (Open Web Text)

Max Activating Token Index: 598

Text #14

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.7952. Min Act: -0.1700

Data Index: 8317310 (Open Web Text)

Max Activating Token Index: 524

Text #15

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.7499. Min Act: -0.1700

Data Index: 7026659 (Open Web Text)

Max Activating Token Index: 974

Text #16

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.7822. Min Act: -0.1700

Data Index: 5804990 (Open Web Text)

Max Activating Token Index: 868

Text #17

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.7964. Min Act: -0.1700

Data Index: 1103094 (Open Web Text)

Max Activating Token Index: 717

Text #18

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.7825. Min Act: -0.1700

Data Index: 3259894 (Open Web Text)

Max Activating Token Index: 502

Text #19

Max Range: 4.1704. Min Range: -4.1704

Max Act: 3.7922. Min Act: -0.1700

Data Index: 2864361 (Open Web Text)

Max Activating Token Index: 307