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

Dataset: Open Web Text

Neuron 2514 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: 5.6422. Min Range: -5.6422

Max Act: 5.6422. Min Act: -0.1700

Data Index: 436472 (Open Web Text)

Max Activating Token Index: 468

Text #1

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.5864. Min Act: -0.1700

Data Index: 1430120 (Open Web Text)

Max Activating Token Index: 726

Text #2

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.5482. Min Act: -0.1700

Data Index: 6388986 (Open Web Text)

Max Activating Token Index: 444

Text #3

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.5581. Min Act: -0.1700

Data Index: 4690707 (Open Web Text)

Max Activating Token Index: 448

Text #4

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.4380. Min Act: -0.1700

Data Index: 4647778 (Open Web Text)

Max Activating Token Index: 895

Text #5

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.3052. Min Act: -0.1700

Data Index: 6747494 (Open Web Text)

Max Activating Token Index: 549

Text #6

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.2951. Min Act: -0.1700

Data Index: 5791953 (Open Web Text)

Max Activating Token Index: 62

Text #7

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.3455. Min Act: -0.1700

Data Index: 5914978 (Open Web Text)

Max Activating Token Index: 46

Text #8

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.2923. Min Act: -0.1700

Data Index: 2670168 (Open Web Text)

Max Activating Token Index: 205

Text #9

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.3242. Min Act: -0.1700

Data Index: 3677182 (Open Web Text)

Max Activating Token Index: 815

Text #10

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.3140. Min Act: -0.1700

Data Index: 6335485 (Open Web Text)

Max Activating Token Index: 435

Text #11

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.3510. Min Act: -0.1700

Data Index: 6246519 (Open Web Text)

Max Activating Token Index: 410

Text #12

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.3297. Min Act: -0.1700

Data Index: 8557436 (Open Web Text)

Max Activating Token Index: 624

Text #13

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.3597. Min Act: -0.1700

Data Index: 4103983 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.2848. Min Act: -0.1700

Data Index: 7214791 (Open Web Text)

Max Activating Token Index: 458

Text #15

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.2366. Min Act: -0.1700

Data Index: 7510529 (Open Web Text)

Max Activating Token Index: 675

Text #16

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.2433. Min Act: -0.1700

Data Index: 7253248 (Open Web Text)

Max Activating Token Index: 546

Text #17

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.2897. Min Act: -0.1700

Data Index: 5271817 (Open Web Text)

Max Activating Token Index: 89

Text #18

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.2055. Min Act: -0.1700

Data Index: 2200992 (Open Web Text)

Max Activating Token Index: 702

Text #19

Max Range: 5.6422. Min Range: -5.6422

Max Act: 5.2630. Min Act: -0.1700

Data Index: 3148524 (Open Web Text)

Max Activating Token Index: 255