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

Dataset: Open Web Text

Neuron 1421 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: 3.8726. Min Range: -3.8726

Max Act: 3.8726. Min Act: -0.1700

Data Index: 100128 (Open Web Text)

Max Activating Token Index: 814

Text #1

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.8421. Min Act: -0.1700

Data Index: 5528552 (Open Web Text)

Max Activating Token Index: 699

Text #2

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.8069. Min Act: -0.1700

Data Index: 6121253 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.7858. Min Act: -0.1700

Data Index: 8762209 (Open Web Text)

Max Activating Token Index: 805

Text #4

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.7437. Min Act: -0.1700

Data Index: 2621228 (Open Web Text)

Max Activating Token Index: 273

Text #5

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.7089. Min Act: -0.1700

Data Index: 5248313 (Open Web Text)

Max Activating Token Index: 404

Text #6

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.7139. Min Act: -0.1700

Data Index: 5695428 (Open Web Text)

Max Activating Token Index: 396

Text #7

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.6865. Min Act: -0.1700

Data Index: 2621229 (Open Web Text)

Max Activating Token Index: 498

Text #8

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.6866. Min Act: -0.1700

Data Index: 2630314 (Open Web Text)

Max Activating Token Index: 853

Text #9

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.6881. Min Act: -0.1700

Data Index: 2413638 (Open Web Text)

Max Activating Token Index: 176

Text #10

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.6846. Min Act: -0.1700

Data Index: 3343476 (Open Web Text)

Max Activating Token Index: 676

Text #11

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.6744. Min Act: -0.1700

Data Index: 883829 (Open Web Text)

Max Activating Token Index: 477

Text #12

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.6736. Min Act: -0.1700

Data Index: 2621227 (Open Web Text)

Max Activating Token Index: 762

Text #13

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.6550. Min Act: -0.1700

Data Index: 60053 (Open Web Text)

Max Activating Token Index: 882

Text #14

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.6387. Min Act: -0.1700

Data Index: 6480030 (Open Web Text)

Max Activating Token Index: 480

Text #15

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.6523. Min Act: -0.1700

Data Index: 5049075 (Open Web Text)

Max Activating Token Index: 693

Text #16

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.6278. Min Act: -0.1700

Data Index: 7230459 (Open Web Text)

Max Activating Token Index: 770

Text #17

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.6239. Min Act: -0.1700

Data Index: 7016560 (Open Web Text)

Max Activating Token Index: 198

Text #18

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.6397. Min Act: -0.1700

Data Index: 4053238 (Open Web Text)

Max Activating Token Index: 788

Text #19

Max Range: 3.8726. Min Range: -3.8726

Max Act: 3.6102. Min Act: -0.1700

Data Index: 4633626 (Open Web Text)

Max Activating Token Index: 379