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

Dataset: Open Web Text

Neuron 1353 in Layer 2

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: 4.4188. Min Range: -4.4188

Max Act: 4.4188. Min Act: -0.1700

Data Index: 1136445 (Open Web Text)

Max Activating Token Index: 194

Text #1

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3745. Min Act: -0.1700

Data Index: 8233865 (Open Web Text)

Max Activating Token Index: 799

Text #2

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.4025. Min Act: -0.1700

Data Index: 5080002 (Open Web Text)

Max Activating Token Index: 350

Text #3

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3935. Min Act: -0.1700

Data Index: 3505483 (Open Web Text)

Max Activating Token Index: 897

Text #4

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3695. Min Act: -0.1700

Data Index: 8130075 (Open Web Text)

Max Activating Token Index: 348

Text #5

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3689. Min Act: -0.1700

Data Index: 1293671 (Open Web Text)

Max Activating Token Index: 350

Text #6

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3656. Min Act: -0.1700

Data Index: 4823774 (Open Web Text)

Max Activating Token Index: 594

Text #7

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3473. Min Act: -0.1700

Data Index: 7202328 (Open Web Text)

Max Activating Token Index: 312

Text #8

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3449. Min Act: -0.1700

Data Index: 3256322 (Open Web Text)

Max Activating Token Index: 806

Text #9

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3473. Min Act: -0.1700

Data Index: 5509424 (Open Web Text)

Max Activating Token Index: 871

Text #10

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3399. Min Act: -0.1700

Data Index: 3189341 (Open Web Text)

Max Activating Token Index: 399

Text #11

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3589. Min Act: -0.1700

Data Index: 1842130 (Open Web Text)

Max Activating Token Index: 567

Text #12

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3233. Min Act: -0.1700

Data Index: 3499865 (Open Web Text)

Max Activating Token Index: 721

Text #13

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3643. Min Act: -0.1700

Data Index: 1080857 (Open Web Text)

Max Activating Token Index: 321

Text #14

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3185. Min Act: -0.1700

Data Index: 4757180 (Open Web Text)

Max Activating Token Index: 468

Text #15

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.2961. Min Act: -0.1700

Data Index: 4341285 (Open Web Text)

Max Activating Token Index: 486

Text #16

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3142. Min Act: -0.1700

Data Index: 2761475 (Open Web Text)

Max Activating Token Index: 904

Text #17

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3206. Min Act: -0.1700

Data Index: 3771160 (Open Web Text)

Max Activating Token Index: 65

Text #18

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3252. Min Act: -0.1700

Data Index: 425485 (Open Web Text)

Max Activating Token Index: 617

Text #19

Max Range: 4.4188. Min Range: -4.4188

Max Act: 4.3083. Min Act: -0.1700

Data Index: 1604758 (Open Web Text)

Max Activating Token Index: 41