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

Dataset: Open Web Text

Neuron 562 in Layer 3

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: 4.6790. Min Range: -4.6790

Max Act: 4.6790. Min Act: -0.1700

Data Index: 5104390 (Open Web Text)

Max Activating Token Index: 266

Text #1

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.6503. Min Act: -0.1700

Data Index: 2248204 (Open Web Text)

Max Activating Token Index: 480

Text #2

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.6246. Min Act: -0.1700

Data Index: 1392531 (Open Web Text)

Max Activating Token Index: 961

Text #3

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.6651. Min Act: -0.1700

Data Index: 4496947 (Open Web Text)

Max Activating Token Index: 560

Text #4

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.6040. Min Act: -0.1700

Data Index: 4496932 (Open Web Text)

Max Activating Token Index: 690

Text #5

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.5329. Min Act: -0.1700

Data Index: 5432830 (Open Web Text)

Max Activating Token Index: 568

Text #6

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.4824. Min Act: -0.1700

Data Index: 1924182 (Open Web Text)

Max Activating Token Index: 615

Text #7

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.4737. Min Act: -0.1700

Data Index: 8247134 (Open Web Text)

Max Activating Token Index: 970

Text #8

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.5138. Min Act: -0.1700

Data Index: 6401697 (Open Web Text)

Max Activating Token Index: 929

Text #9

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.4638. Min Act: -0.1700

Data Index: 1167508 (Open Web Text)

Max Activating Token Index: 329

Text #10

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.5008. Min Act: -0.1700

Data Index: 5906558 (Open Web Text)

Max Activating Token Index: 423

Text #11

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.4527. Min Act: -0.1700

Data Index: 1007741 (Open Web Text)

Max Activating Token Index: 330

Text #12

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.4853. Min Act: -0.1700

Data Index: 8250485 (Open Web Text)

Max Activating Token Index: 330

Text #13

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.3905. Min Act: -0.1700

Data Index: 8237689 (Open Web Text)

Max Activating Token Index: 758

Text #14

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.3942. Min Act: -0.1700

Data Index: 3538195 (Open Web Text)

Max Activating Token Index: 183

Text #15

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.4611. Min Act: -0.1700

Data Index: 7407619 (Open Web Text)

Max Activating Token Index: 42

Text #16

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.4315. Min Act: -0.1700

Data Index: 2066151 (Open Web Text)

Max Activating Token Index: 329

Text #17

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.4565. Min Act: -0.1700

Data Index: 7256253 (Open Web Text)

Max Activating Token Index: 44

Text #18

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.3661. Min Act: -0.1700

Data Index: 3912247 (Open Web Text)

Max Activating Token Index: 434

Text #19

Max Range: 4.6790. Min Range: -4.6790

Max Act: 4.3726. Min Act: -0.1700

Data Index: 510509 (Open Web Text)

Max Activating Token Index: 699