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

Dataset: Open Web Text

Neuron 957 in Layer 1

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: 5.0270. Min Range: -5.0270

Max Act: 5.0270. Min Act: -0.1700

Data Index: 4958421 (Open Web Text)

Max Activating Token Index: 1021

Text #1

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.9902. Min Act: -0.1700

Data Index: 3435575 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.9756. Min Act: -0.1700

Data Index: 2686813 (Open Web Text)

Max Activating Token Index: 731

Text #3

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.9690. Min Act: -0.1700

Data Index: 5094425 (Open Web Text)

Max Activating Token Index: 719

Text #4

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.9599. Min Act: -0.1700

Data Index: 8571986 (Open Web Text)

Max Activating Token Index: 659

Text #5

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.9250. Min Act: -0.1700

Data Index: 5072002 (Open Web Text)

Max Activating Token Index: 86

Text #6

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.9278. Min Act: -0.1700

Data Index: 4218593 (Open Web Text)

Max Activating Token Index: 939

Text #7

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.9018. Min Act: -0.1700

Data Index: 2218669 (Open Web Text)

Max Activating Token Index: 597

Text #8

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.9029. Min Act: -0.1700

Data Index: 6024746 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.8869. Min Act: -0.1700

Data Index: 6260764 (Open Web Text)

Max Activating Token Index: 606

Text #10

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.8922. Min Act: -0.1700

Data Index: 4108943 (Open Web Text)

Max Activating Token Index: 124

Text #11

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.8977. Min Act: -0.1700

Data Index: 3138306 (Open Web Text)

Max Activating Token Index: 350

Text #12

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.9011. Min Act: -0.1700

Data Index: 7970443 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.8499. Min Act: -0.1700

Data Index: 3355440 (Open Web Text)

Max Activating Token Index: 613

Text #14

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.8647. Min Act: -0.1700

Data Index: 4557329 (Open Web Text)

Max Activating Token Index: 429

Text #15

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.8677. Min Act: -0.1700

Data Index: 8150139 (Open Web Text)

Max Activating Token Index: 35

Text #16

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.8626. Min Act: -0.1700

Data Index: 4331623 (Open Web Text)

Max Activating Token Index: 573

Text #17

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.8506. Min Act: -0.1700

Data Index: 5655656 (Open Web Text)

Max Activating Token Index: 569

Text #18

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.8180. Min Act: -0.1700

Data Index: 881187 (Open Web Text)

Max Activating Token Index: 112

Text #19

Max Range: 5.0270. Min Range: -5.0270

Max Act: 4.8474. Min Act: -0.1700

Data Index: 4734240 (Open Web Text)

Max Activating Token Index: 530