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

Dataset: Open Web Text

Neuron 1398 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: 3.2726. Min Range: -3.2726

Max Act: 3.2726. Min Act: -0.1700

Data Index: 2272514 (Open Web Text)

Max Activating Token Index: 548

Text #1

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.1842. Min Act: -0.1700

Data Index: 4296502 (Open Web Text)

Max Activating Token Index: 28

Text #2

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.1739. Min Act: -0.1700

Data Index: 3996904 (Open Web Text)

Max Activating Token Index: 869

Text #3

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.1646. Min Act: -0.1700

Data Index: 8061104 (Open Web Text)

Max Activating Token Index: 58

Text #4

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.1533. Min Act: -0.1700

Data Index: 1336787 (Open Web Text)

Max Activating Token Index: 22

Text #5

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.1560. Min Act: -0.1700

Data Index: 953544 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.1337. Min Act: -0.1700

Data Index: 344637 (Open Web Text)

Max Activating Token Index: 265

Text #7

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.1358. Min Act: -0.1700

Data Index: 6157863 (Open Web Text)

Max Activating Token Index: 141

Text #8

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.1529. Min Act: -0.1700

Data Index: 8103360 (Open Web Text)

Max Activating Token Index: 917

Text #9

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.1185. Min Act: -0.1700

Data Index: 4436875 (Open Web Text)

Max Activating Token Index: 459

Text #10

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.0981. Min Act: -0.1700

Data Index: 2949652 (Open Web Text)

Max Activating Token Index: 812

Text #11

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.0943. Min Act: -0.1700

Data Index: 4449348 (Open Web Text)

Max Activating Token Index: 789

Text #12

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.0627. Min Act: -0.1700

Data Index: 5184950 (Open Web Text)

Max Activating Token Index: 810

Text #13

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.0850. Min Act: -0.1700

Data Index: 296666 (Open Web Text)

Max Activating Token Index: 384

Text #14

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.0693. Min Act: -0.1700

Data Index: 7741205 (Open Web Text)

Max Activating Token Index: 37

Text #15

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.0624. Min Act: -0.1700

Data Index: 2044539 (Open Web Text)

Max Activating Token Index: 280

Text #16

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.0614. Min Act: -0.1700

Data Index: 367878 (Open Web Text)

Max Activating Token Index: 650

Text #17

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.0665. Min Act: -0.1700

Data Index: 422603 (Open Web Text)

Max Activating Token Index: 716

Text #18

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.0608. Min Act: -0.1700

Data Index: 5022772 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 3.2726. Min Range: -3.2726

Max Act: 3.0360. Min Act: -0.1700

Data Index: 1747034 (Open Web Text)

Max Activating Token Index: 5