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

Dataset: Open Web Text

Neuron 2359 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: 3.0285. Min Range: -3.0285

Max Act: 3.0285. Min Act: -0.1700

Data Index: 3049374 (Open Web Text)

Max Activating Token Index: 932

Text #1

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.9290. Min Act: -0.1700

Data Index: 2768963 (Open Web Text)

Max Activating Token Index: 367

Text #2

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.8837. Min Act: -0.1700

Data Index: 6686166 (Open Web Text)

Max Activating Token Index: 287

Text #3

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.8849. Min Act: -0.1700

Data Index: 7641831 (Open Web Text)

Max Activating Token Index: 407

Text #4

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.8768. Min Act: -0.1700

Data Index: 155626 (Open Web Text)

Max Activating Token Index: 594

Text #5

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.8316. Min Act: -0.1700

Data Index: 7217739 (Open Web Text)

Max Activating Token Index: 227

Text #6

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.8477. Min Act: -0.1700

Data Index: 241377 (Open Web Text)

Max Activating Token Index: 598

Text #7

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.8378. Min Act: -0.1700

Data Index: 710030 (Open Web Text)

Max Activating Token Index: 866

Text #8

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.8169. Min Act: -0.1700

Data Index: 2927373 (Open Web Text)

Max Activating Token Index: 237

Text #9

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.8172. Min Act: -0.1700

Data Index: 1954792 (Open Web Text)

Max Activating Token Index: 367

Text #10

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.7865. Min Act: -0.1700

Data Index: 4124200 (Open Web Text)

Max Activating Token Index: 585

Text #11

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.7896. Min Act: -0.1700

Data Index: 7677192 (Open Web Text)

Max Activating Token Index: 578

Text #12

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.7619. Min Act: -0.1700

Data Index: 7660369 (Open Web Text)

Max Activating Token Index: 862

Text #13

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.7661. Min Act: -0.1700

Data Index: 4608797 (Open Web Text)

Max Activating Token Index: 341

Text #14

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.7586. Min Act: -0.1700

Data Index: 2090416 (Open Web Text)

Max Activating Token Index: 36

Text #15

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.7648. Min Act: -0.1700

Data Index: 8663739 (Open Web Text)

Max Activating Token Index: 483

Text #16

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.7507. Min Act: -0.1700

Data Index: 3256937 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.7328. Min Act: -0.1700

Data Index: 4685430 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.7470. Min Act: -0.1700

Data Index: 260109 (Open Web Text)

Max Activating Token Index: 927

Text #19

Max Range: 3.0285. Min Range: -3.0285

Max Act: 2.7228. Min Act: -0.1700

Data Index: 48061 (Open Web Text)

Max Activating Token Index: 906