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

Dataset: Open Web Text

Neuron 1351 in Layer 2

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: 1.5395. Min Range: -1.5395

Max Act: 1.5268. Min Act: -0.1700

Data Index: 1999671 (Open Web Text)

Max Activating Token Index: 593

Text #1

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.5395. Min Act: -0.1700

Data Index: 3195579 (Open Web Text)

Max Activating Token Index: 483

Text #2

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.5008. Min Act: -0.1700

Data Index: 3007379 (Open Web Text)

Max Activating Token Index: 21

Text #3

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4909. Min Act: -0.1699

Data Index: 6473134 (Open Web Text)

Max Activating Token Index: 937

Text #4

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4725. Min Act: -0.1700

Data Index: 8160509 (Open Web Text)

Max Activating Token Index: 428

Text #5

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4638. Min Act: -0.1700

Data Index: 7701189 (Open Web Text)

Max Activating Token Index: 855

Text #6

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4656. Min Act: -0.1698

Data Index: 3377194 (Open Web Text)

Max Activating Token Index: 662

Text #7

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4586. Min Act: -0.1700

Data Index: 4816133 (Open Web Text)

Max Activating Token Index: 311

Text #8

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4610. Min Act: -0.1700

Data Index: 6545391 (Open Web Text)

Max Activating Token Index: 83

Text #9

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4526. Min Act: -0.1698

Data Index: 606597 (Open Web Text)

Max Activating Token Index: 243

Text #10

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4527. Min Act: -0.1700

Data Index: 8442804 (Open Web Text)

Max Activating Token Index: 74

Text #11

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4643. Min Act: -0.1700

Data Index: 947318 (Open Web Text)

Max Activating Token Index: 47

Text #12

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4510. Min Act: -0.1700

Data Index: 4619709 (Open Web Text)

Max Activating Token Index: 595

Text #13

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4527. Min Act: -0.1700

Data Index: 6718805 (Open Web Text)

Max Activating Token Index: 322

Text #14

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4458. Min Act: -0.1700

Data Index: 1465630 (Open Web Text)

Max Activating Token Index: 957

Text #15

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4573. Min Act: -0.1696

Data Index: 3478457 (Open Web Text)

Max Activating Token Index: 239

Text #16

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4421. Min Act: -0.1698

Data Index: 1370853 (Open Web Text)

Max Activating Token Index: 729

Text #17

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4543. Min Act: -0.1694

Data Index: 8434968 (Open Web Text)

Max Activating Token Index: 547

Text #18

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4420. Min Act: -0.1682

Data Index: 3282574 (Open Web Text)

Max Activating Token Index: 138

Text #19

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.4389. Min Act: -0.1700

Data Index: 7193892 (Open Web Text)

Max Activating Token Index: 503