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

Dataset: Open Web Text

Neuron 1642 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: 7.9768. Min Range: -7.9768

Max Act: 7.9768. Min Act: -0.1700

Data Index: 1396006 (Open Web Text)

Max Activating Token Index: 213

Text #1

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.7549. Min Act: -0.1700

Data Index: 1461866 (Open Web Text)

Max Activating Token Index: 262

Text #2

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.6462. Min Act: -0.1700

Data Index: 2393574 (Open Web Text)

Max Activating Token Index: 509

Text #3

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.5806. Min Act: -0.1700

Data Index: 7061920 (Open Web Text)

Max Activating Token Index: 749

Text #4

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.5095. Min Act: -0.1700

Data Index: 2434913 (Open Web Text)

Max Activating Token Index: 525

Text #5

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.4468. Min Act: -0.1700

Data Index: 5879131 (Open Web Text)

Max Activating Token Index: 839

Text #6

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.4708. Min Act: -0.1700

Data Index: 1849246 (Open Web Text)

Max Activating Token Index: 924

Text #7

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.4149. Min Act: -0.1700

Data Index: 175249 (Open Web Text)

Max Activating Token Index: 781

Text #8

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.3289. Min Act: -0.1700

Data Index: 7678461 (Open Web Text)

Max Activating Token Index: 810

Text #9

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.3415. Min Act: -0.1700

Data Index: 5380316 (Open Web Text)

Max Activating Token Index: 727

Text #10

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.2038. Min Act: -0.1700

Data Index: 5701064 (Open Web Text)

Max Activating Token Index: 926

Text #11

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.3070. Min Act: -0.1700

Data Index: 2023716 (Open Web Text)

Max Activating Token Index: 454

Text #12

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.2594. Min Act: -0.1700

Data Index: 4786082 (Open Web Text)

Max Activating Token Index: 384

Text #13

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.2274. Min Act: -0.1700

Data Index: 4938005 (Open Web Text)

Max Activating Token Index: 741

Text #14

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.2467. Min Act: -0.1700

Data Index: 3239434 (Open Web Text)

Max Activating Token Index: 443

Text #15

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.2155. Min Act: -0.1700

Data Index: 4992022 (Open Web Text)

Max Activating Token Index: 114

Text #16

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.1508. Min Act: -0.1700

Data Index: 7462654 (Open Web Text)

Max Activating Token Index: 909

Text #17

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.2480. Min Act: -0.1700

Data Index: 452232 (Open Web Text)

Max Activating Token Index: 899

Text #18

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.2257. Min Act: -0.1700

Data Index: 4499854 (Open Web Text)

Max Activating Token Index: 917

Text #19

Max Range: 7.9768. Min Range: -7.9768

Max Act: 7.1876. Min Act: -0.1700

Data Index: 2175922 (Open Web Text)

Max Activating Token Index: 298