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

Dataset: Open Web Text

Neuron 1990 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: 2.8726. Min Range: -2.8726

Max Act: 2.8726. Min Act: -0.1700

Data Index: 4778561 (Open Web Text)

Max Activating Token Index: 221

Text #1

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.7161. Min Act: -0.1700

Data Index: 3771927 (Open Web Text)

Max Activating Token Index: 37

Text #2

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.6675. Min Act: -0.1700

Data Index: 4901250 (Open Web Text)

Max Activating Token Index: 391

Text #3

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.6319. Min Act: -0.1700

Data Index: 1834427 (Open Web Text)

Max Activating Token Index: 605

Text #4

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.6598. Min Act: -0.1700

Data Index: 8720841 (Open Web Text)

Max Activating Token Index: 997

Text #5

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.6425. Min Act: -0.1700

Data Index: 384153 (Open Web Text)

Max Activating Token Index: 65

Text #6

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.5938. Min Act: -0.1700

Data Index: 1479970 (Open Web Text)

Max Activating Token Index: 601

Text #7

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.5961. Min Act: -0.1700

Data Index: 4109996 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.5920. Min Act: -0.1700

Data Index: 3437296 (Open Web Text)

Max Activating Token Index: 901

Text #9

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.5909. Min Act: -0.1700

Data Index: 870034 (Open Web Text)

Max Activating Token Index: 511

Text #10

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.5615. Min Act: -0.1700

Data Index: 7061094 (Open Web Text)

Max Activating Token Index: 472

Text #11

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.5673. Min Act: -0.1700

Data Index: 8379087 (Open Web Text)

Max Activating Token Index: 186

Text #12

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.5674. Min Act: -0.1700

Data Index: 1179083 (Open Web Text)

Max Activating Token Index: 251

Text #13

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.5417. Min Act: -0.1700

Data Index: 551619 (Open Web Text)

Max Activating Token Index: 53

Text #14

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.5592. Min Act: -0.1700

Data Index: 3574291 (Open Web Text)

Max Activating Token Index: 275

Text #15

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.5560. Min Act: -0.1700

Data Index: 8247476 (Open Web Text)

Max Activating Token Index: 637

Text #16

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.5352. Min Act: -0.1700

Data Index: 4440346 (Open Web Text)

Max Activating Token Index: 757

Text #17

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.5200. Min Act: -0.1700

Data Index: 6496510 (Open Web Text)

Max Activating Token Index: 745

Text #18

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.5316. Min Act: -0.1700

Data Index: 53253 (Open Web Text)

Max Activating Token Index: 558

Text #19

Max Range: 2.8726. Min Range: -2.8726

Max Act: 2.5035. Min Act: -0.1700

Data Index: 4888581 (Open Web Text)

Max Activating Token Index: 219