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

Dataset: Open Web Text

Neuron 2545 in Layer 4

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: 3.1482. Min Range: -3.1482

Max Act: 3.1482. Min Act: -0.1700

Data Index: 1385202 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.1204. Min Act: -0.1700

Data Index: 5731309 (Open Web Text)

Max Activating Token Index: 394

Text #2

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.1193. Min Act: -0.1700

Data Index: 4820651 (Open Web Text)

Max Activating Token Index: 711

Text #3

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.1238. Min Act: -0.1700

Data Index: 8375256 (Open Web Text)

Max Activating Token Index: 505

Text #4

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.1116. Min Act: -0.1700

Data Index: 7965911 (Open Web Text)

Max Activating Token Index: 943

Text #5

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.1053. Min Act: -0.1700

Data Index: 6633287 (Open Web Text)

Max Activating Token Index: 501

Text #6

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.1013. Min Act: -0.1700

Data Index: 4041794 (Open Web Text)

Max Activating Token Index: 958

Text #7

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0879. Min Act: -0.1700

Data Index: 8119923 (Open Web Text)

Max Activating Token Index: 53

Text #8

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0696. Min Act: -0.1700

Data Index: 1438640 (Open Web Text)

Max Activating Token Index: 321

Text #9

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0768. Min Act: -0.1700

Data Index: 1623860 (Open Web Text)

Max Activating Token Index: 574

Text #10

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0693. Min Act: -0.1700

Data Index: 6667860 (Open Web Text)

Max Activating Token Index: 89

Text #11

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0813. Min Act: -0.1700

Data Index: 1739862 (Open Web Text)

Max Activating Token Index: 525

Text #12

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0618. Min Act: -0.1700

Data Index: 6668628 (Open Web Text)

Max Activating Token Index: 895

Text #13

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0649. Min Act: -0.1700

Data Index: 4003708 (Open Web Text)

Max Activating Token Index: 666

Text #14

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0777. Min Act: -0.1700

Data Index: 4013895 (Open Web Text)

Max Activating Token Index: 433

Text #15

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0671. Min Act: -0.1700

Data Index: 7632185 (Open Web Text)

Max Activating Token Index: 593

Text #16

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0475. Min Act: -0.1700

Data Index: 2727715 (Open Web Text)

Max Activating Token Index: 330

Text #17

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0494. Min Act: -0.1700

Data Index: 729954 (Open Web Text)

Max Activating Token Index: 275

Text #18

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0531. Min Act: -0.1700

Data Index: 7836231 (Open Web Text)

Max Activating Token Index: 935

Text #19

Max Range: 3.1482. Min Range: -3.1482

Max Act: 3.0293. Min Act: -0.1700

Data Index: 4820025 (Open Web Text)

Max Activating Token Index: 784