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

Dataset: Open Web Text

Neuron 2053 in Layer 0

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: 4.3353. Min Range: -4.3353

Max Act: 4.3237. Min Act: -0.1282

Data Index: 2041706 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.3353. Min Act: -0.1700

Data Index: 1217199 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1879. Min Act: -0.1360

Data Index: 1117221 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1737. Min Act: -0.1700

Data Index: 3706243 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1879. Min Act: -0.1694

Data Index: 7347717 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1525. Min Act: -0.1554

Data Index: 1783904 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1388. Min Act: -0.1426

Data Index: 3955872 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1522. Min Act: -0.1700

Data Index: 6833772 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1314. Min Act: -0.1698

Data Index: 3064779 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1525. Min Act: -0.1358

Data Index: 377662 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1525. Min Act: -0.1489

Data Index: 7029347 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1313. Min Act: -0.1673

Data Index: 5139669 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1423. Min Act: -0.1699

Data Index: 4225019 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1388. Min Act: -0.1481

Data Index: 3987971 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1023. Min Act: -0.1329

Data Index: 8528724 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1265. Min Act: -0.1697

Data Index: 2883976 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1325. Min Act: -0.1684

Data Index: 5616467 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.1063. Min Act: -0.1620

Data Index: 7412417 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.0887. Min Act: -0.1688

Data Index: 5923159 (Open Web Text)

Max Activating Token Index: 309

Text #19

Max Range: 4.3353. Min Range: -4.3353

Max Act: 4.0789. Min Act: -0.1267

Data Index: 6306169 (Open Web Text)

Max Activating Token Index: 641