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

Dataset: Open Web Text

Neuron 230 in Layer 4

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: 4.9646. Min Range: -4.9646

Max Act: 4.9646. Min Act: -0.1700

Data Index: 6504211 (Open Web Text)

Max Activating Token Index: 763

Text #1

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.8026. Min Act: -0.1700

Data Index: 38650 (Open Web Text)

Max Activating Token Index: 648

Text #2

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.7717. Min Act: -0.1700

Data Index: 7577015 (Open Web Text)

Max Activating Token Index: 721

Text #3

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.8246. Min Act: -0.1700

Data Index: 934953 (Open Web Text)

Max Activating Token Index: 627

Text #4

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.7680. Min Act: -0.1700

Data Index: 1102550 (Open Web Text)

Max Activating Token Index: 381

Text #5

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.7267. Min Act: -0.1700

Data Index: 2768573 (Open Web Text)

Max Activating Token Index: 672

Text #6

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.7363. Min Act: -0.1700

Data Index: 1906546 (Open Web Text)

Max Activating Token Index: 503

Text #7

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.7384. Min Act: -0.1700

Data Index: 7290917 (Open Web Text)

Max Activating Token Index: 634

Text #8

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.7057. Min Act: -0.1700

Data Index: 4885198 (Open Web Text)

Max Activating Token Index: 448

Text #9

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.7194. Min Act: -0.1700

Data Index: 7348303 (Open Web Text)

Max Activating Token Index: 432

Text #10

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.6984. Min Act: -0.1700

Data Index: 2125709 (Open Web Text)

Max Activating Token Index: 706

Text #11

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.6433. Min Act: -0.1700

Data Index: 3470109 (Open Web Text)

Max Activating Token Index: 573

Text #12

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.6523. Min Act: -0.1700

Data Index: 6093978 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.6347. Min Act: -0.1700

Data Index: 2131232 (Open Web Text)

Max Activating Token Index: 462

Text #14

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.6251. Min Act: -0.1700

Data Index: 5796998 (Open Web Text)

Max Activating Token Index: 820

Text #15

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.5956. Min Act: -0.1700

Data Index: 1826376 (Open Web Text)

Max Activating Token Index: 471

Text #16

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.6138. Min Act: -0.1700

Data Index: 1168983 (Open Web Text)

Max Activating Token Index: 228

Text #17

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.5896. Min Act: -0.1700

Data Index: 2148574 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.6093. Min Act: -0.1700

Data Index: 6092261 (Open Web Text)

Max Activating Token Index: 138

Text #19

Max Range: 4.9646. Min Range: -4.9646

Max Act: 4.6378. Min Act: -0.1700

Data Index: 4578731 (Open Web Text)

Max Activating Token Index: 178