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

Dataset: Open Web Text

Neuron 1878 in Layer 6

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: 3.4755. Min Range: -3.4755

Max Act: 3.4755. Min Act: -0.1700

Data Index: 638540 (Open Web Text)

Max Activating Token Index: 811

Text #1

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.3985. Min Act: -0.1700

Data Index: 7795107 (Open Web Text)

Max Activating Token Index: 861

Text #2

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2706. Min Act: -0.1700

Data Index: 3757090 (Open Web Text)

Max Activating Token Index: 757

Text #3

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2711. Min Act: -0.1700

Data Index: 5373399 (Open Web Text)

Max Activating Token Index: 1010

Text #4

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2581. Min Act: -0.1700

Data Index: 6882510 (Open Web Text)

Max Activating Token Index: 553

Text #5

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2489. Min Act: -0.1700

Data Index: 8622250 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2619. Min Act: -0.1700

Data Index: 1910672 (Open Web Text)

Max Activating Token Index: 458

Text #7

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2614. Min Act: -0.1700

Data Index: 289632 (Open Web Text)

Max Activating Token Index: 777

Text #8

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2378. Min Act: -0.1700

Data Index: 196478 (Open Web Text)

Max Activating Token Index: 989

Text #9

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2356. Min Act: -0.1700

Data Index: 3765282 (Open Web Text)

Max Activating Token Index: 786

Text #10

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2238. Min Act: -0.1700

Data Index: 6385620 (Open Web Text)

Max Activating Token Index: 440

Text #11

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2521. Min Act: -0.1700

Data Index: 7917341 (Open Web Text)

Max Activating Token Index: 476

Text #12

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2408. Min Act: -0.1700

Data Index: 4098030 (Open Web Text)

Max Activating Token Index: 609

Text #13

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2131. Min Act: -0.1700

Data Index: 4697316 (Open Web Text)

Max Activating Token Index: 633

Text #14

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2135. Min Act: -0.1700

Data Index: 647318 (Open Web Text)

Max Activating Token Index: 303

Text #15

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2027. Min Act: -0.1700

Data Index: 2068017 (Open Web Text)

Max Activating Token Index: 991

Text #16

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2108. Min Act: -0.1700

Data Index: 7218353 (Open Web Text)

Max Activating Token Index: 909

Text #17

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.1972. Min Act: -0.1700

Data Index: 879835 (Open Web Text)

Max Activating Token Index: 884

Text #18

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.2045. Min Act: -0.1700

Data Index: 8126481 (Open Web Text)

Max Activating Token Index: 362

Text #19

Max Range: 3.4755. Min Range: -3.4755

Max Act: 3.1635. Min Act: -0.1700

Data Index: 4888040 (Open Web Text)

Max Activating Token Index: 559