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

Dataset: Open Web Text

Neuron 216 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: 2.3805. Min Range: -2.3805

Max Act: 2.3805. Min Act: -0.1700

Data Index: 1628182 (Open Web Text)

Max Activating Token Index: 381

Text #1

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.3737. Min Act: -0.1700

Data Index: 575836 (Open Web Text)

Max Activating Token Index: 150

Text #2

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.3509. Min Act: -0.1700

Data Index: 3021351 (Open Web Text)

Max Activating Token Index: 843

Text #3

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.3306. Min Act: -0.1700

Data Index: 1980634 (Open Web Text)

Max Activating Token Index: 384

Text #4

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.3044. Min Act: -0.1700

Data Index: 8826890 (Open Web Text)

Max Activating Token Index: 696

Text #5

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.3051. Min Act: -0.1700

Data Index: 5225620 (Open Web Text)

Max Activating Token Index: 988

Text #6

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.3060. Min Act: -0.1700

Data Index: 973998 (Open Web Text)

Max Activating Token Index: 270

Text #7

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2849. Min Act: -0.1700

Data Index: 1354285 (Open Web Text)

Max Activating Token Index: 918

Text #8

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2796. Min Act: -0.1700

Data Index: 703861 (Open Web Text)

Max Activating Token Index: 503

Text #9

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2972. Min Act: -0.1700

Data Index: 1539282 (Open Web Text)

Max Activating Token Index: 404

Text #10

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2644. Min Act: -0.1700

Data Index: 6396194 (Open Web Text)

Max Activating Token Index: 153

Text #11

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2842. Min Act: -0.1700

Data Index: 1623238 (Open Web Text)

Max Activating Token Index: 977

Text #12

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2753. Min Act: -0.1700

Data Index: 4528805 (Open Web Text)

Max Activating Token Index: 886

Text #13

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2743. Min Act: -0.1700

Data Index: 3133861 (Open Web Text)

Max Activating Token Index: 547

Text #14

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2744. Min Act: -0.1700

Data Index: 7743049 (Open Web Text)

Max Activating Token Index: 419

Text #15

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2687. Min Act: -0.1700

Data Index: 6369884 (Open Web Text)

Max Activating Token Index: 578

Text #16

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2566. Min Act: -0.1700

Data Index: 8088644 (Open Web Text)

Max Activating Token Index: 737

Text #17

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2330. Min Act: -0.1700

Data Index: 6228324 (Open Web Text)

Max Activating Token Index: 514

Text #18

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2260. Min Act: -0.1700

Data Index: 4176411 (Open Web Text)

Max Activating Token Index: 448

Text #19

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2236. Min Act: -0.1700

Data Index: 2934114 (Open Web Text)

Max Activating Token Index: 540