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

Dataset: Open Web Text

Neuron 2077 in Layer 1

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: 4.6562. Min Range: -4.6562

Max Act: 4.6562. Min Act: -0.1700

Data Index: 5079580 (Open Web Text)

Max Activating Token Index: 393

Text #1

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.6385. Min Act: -0.1700

Data Index: 1482539 (Open Web Text)

Max Activating Token Index: 622

Text #2

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.6284. Min Act: -0.1700

Data Index: 8417450 (Open Web Text)

Max Activating Token Index: 677

Text #3

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.6303. Min Act: -0.1700

Data Index: 3397647 (Open Web Text)

Max Activating Token Index: 801

Text #4

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.6012. Min Act: -0.1700

Data Index: 1733158 (Open Web Text)

Max Activating Token Index: 379

Text #5

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.5645. Min Act: -0.1700

Data Index: 5088928 (Open Web Text)

Max Activating Token Index: 284

Text #6

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.5658. Min Act: -0.1700

Data Index: 5088926 (Open Web Text)

Max Activating Token Index: 743

Text #7

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.5671. Min Act: -0.1700

Data Index: 910838 (Open Web Text)

Max Activating Token Index: 628

Text #8

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.5579. Min Act: -0.1700

Data Index: 716566 (Open Web Text)

Max Activating Token Index: 483

Text #9

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.4974. Min Act: -0.1700

Data Index: 7304432 (Open Web Text)

Max Activating Token Index: 75

Text #10

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.4874. Min Act: -0.1700

Data Index: 5059582 (Open Web Text)

Max Activating Token Index: 930

Text #11

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.5008. Min Act: -0.1700

Data Index: 2330828 (Open Web Text)

Max Activating Token Index: 536

Text #12

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.5015. Min Act: -0.1700

Data Index: 2250739 (Open Web Text)

Max Activating Token Index: 56

Text #13

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.4831. Min Act: -0.1700

Data Index: 6833710 (Open Web Text)

Max Activating Token Index: 839

Text #14

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.4877. Min Act: -0.1700

Data Index: 757980 (Open Web Text)

Max Activating Token Index: 505

Text #15

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.5130. Min Act: -0.1700

Data Index: 3906836 (Open Web Text)

Max Activating Token Index: 364

Text #16

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.4902. Min Act: -0.1700

Data Index: 6254646 (Open Web Text)

Max Activating Token Index: 413

Text #17

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.4703. Min Act: -0.1700

Data Index: 5788911 (Open Web Text)

Max Activating Token Index: 194

Text #18

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.4782. Min Act: -0.1700

Data Index: 5693069 (Open Web Text)

Max Activating Token Index: 481

Text #19

Max Range: 4.6562. Min Range: -4.6562

Max Act: 4.5084. Min Act: -0.1700

Data Index: 2812558 (Open Web Text)

Max Activating Token Index: 325