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

Dataset: Open Web Text

Neuron 1081 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: 1.8727. Min Range: -1.8727

Max Act: 1.8727. Min Act: -0.1281

Data Index: 8116752 (Open Web Text)

Max Activating Token Index: 338

Text #1

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.8493. Min Act: -0.1477

Data Index: 2648883 (Open Web Text)

Max Activating Token Index: 229

Text #2

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.8070. Min Act: -0.1675

Data Index: 844206 (Open Web Text)

Max Activating Token Index: 157

Text #3

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.8055. Min Act: -0.1658

Data Index: 5061169 (Open Web Text)

Max Activating Token Index: 186

Text #4

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7732. Min Act: -0.1672

Data Index: 288609 (Open Web Text)

Max Activating Token Index: 439

Text #5

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7712. Min Act: -0.1369

Data Index: 5586921 (Open Web Text)

Max Activating Token Index: 694

Text #6

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7597. Min Act: -0.1616

Data Index: 703400 (Open Web Text)

Max Activating Token Index: 546

Text #7

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7536. Min Act: -0.0946

Data Index: 8276353 (Open Web Text)

Max Activating Token Index: 540

Text #8

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7405. Min Act: -0.1549

Data Index: 8421238 (Open Web Text)

Max Activating Token Index: 509

Text #9

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7500. Min Act: -0.1503

Data Index: 8191287 (Open Web Text)

Max Activating Token Index: 33

Text #10

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7343. Min Act: -0.1247

Data Index: 1253519 (Open Web Text)

Max Activating Token Index: 507

Text #11

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7329. Min Act: -0.1629

Data Index: 178853 (Open Web Text)

Max Activating Token Index: 661

Text #12

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7297. Min Act: -0.1385

Data Index: 972876 (Open Web Text)

Max Activating Token Index: 671

Text #13

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7291. Min Act: -0.1207

Data Index: 5314414 (Open Web Text)

Max Activating Token Index: 710

Text #14

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7158. Min Act: -0.1121

Data Index: 7211531 (Open Web Text)

Max Activating Token Index: 726

Text #15

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7198. Min Act: -0.1105

Data Index: 6388528 (Open Web Text)

Max Activating Token Index: 481

Text #16

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7075. Min Act: -0.1396

Data Index: 6772776 (Open Web Text)

Max Activating Token Index: 680

Text #17

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7023. Min Act: -0.1497

Data Index: 2189842 (Open Web Text)

Max Activating Token Index: 725

Text #18

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7114. Min Act: -0.1300

Data Index: 6144202 (Open Web Text)

Max Activating Token Index: 548

Text #19

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7055. Min Act: -0.1192

Data Index: 5157038 (Open Web Text)

Max Activating Token Index: 751