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

Dataset: Open Web Text

Neuron 477 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: 3.3943. Min Range: -3.3943

Max Act: 3.3943. Min Act: -0.1700

Data Index: 8463656 (Open Web Text)

Max Activating Token Index: 695

Text #1

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.3480. Min Act: -0.1700

Data Index: 6025142 (Open Web Text)

Max Activating Token Index: 374

Text #2

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.3194. Min Act: -0.1700

Data Index: 3374737 (Open Web Text)

Max Activating Token Index: 23

Text #3

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.2871. Min Act: -0.1700

Data Index: 6062289 (Open Web Text)

Max Activating Token Index: 288

Text #4

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.2551. Min Act: -0.1700

Data Index: 3999416 (Open Web Text)

Max Activating Token Index: 803

Text #5

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.2877. Min Act: -0.1700

Data Index: 1872116 (Open Web Text)

Max Activating Token Index: 285

Text #6

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.2365. Min Act: -0.1700

Data Index: 5762112 (Open Web Text)

Max Activating Token Index: 633

Text #7

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.1974. Min Act: -0.1700

Data Index: 2592514 (Open Web Text)

Max Activating Token Index: 517

Text #8

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.2207. Min Act: -0.1700

Data Index: 5276427 (Open Web Text)

Max Activating Token Index: 397

Text #9

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.2182. Min Act: -0.1700

Data Index: 154650 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.1830. Min Act: -0.1700

Data Index: 7673574 (Open Web Text)

Max Activating Token Index: 82

Text #11

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.2276. Min Act: -0.1700

Data Index: 6942616 (Open Web Text)

Max Activating Token Index: 415

Text #12

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.1874. Min Act: -0.1700

Data Index: 5386720 (Open Web Text)

Max Activating Token Index: 294

Text #13

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.1761. Min Act: -0.1700

Data Index: 7953427 (Open Web Text)

Max Activating Token Index: 632

Text #14

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.2095. Min Act: -0.1700

Data Index: 1513501 (Open Web Text)

Max Activating Token Index: 158

Text #15

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.1616. Min Act: -0.1700

Data Index: 7465306 (Open Web Text)

Max Activating Token Index: 445

Text #16

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.1584. Min Act: -0.1700

Data Index: 5061495 (Open Web Text)

Max Activating Token Index: 680

Text #17

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.1618. Min Act: -0.1700

Data Index: 3407025 (Open Web Text)

Max Activating Token Index: 355

Text #18

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.0641. Min Act: -0.1700

Data Index: 5113537 (Open Web Text)

Max Activating Token Index: 454

Text #19

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.1429. Min Act: -0.1700

Data Index: 3606110 (Open Web Text)

Max Activating Token Index: 931