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

Dataset: Open Web Text

Neuron 565 in Layer 3

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: 3.0541. Min Range: -3.0541

Max Act: 3.0541. Min Act: -0.1700

Data Index: 3385568 (Open Web Text)

Max Activating Token Index: 624

Text #1

Max Range: 3.0541. Min Range: -3.0541

Max Act: 3.0467. Min Act: -0.1700

Data Index: 8365005 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 3.0541. Min Range: -3.0541

Max Act: 3.0513. Min Act: -0.1700

Data Index: 1275710 (Open Web Text)

Max Activating Token Index: 544

Text #3

Max Range: 3.0541. Min Range: -3.0541

Max Act: 3.0291. Min Act: -0.1700

Data Index: 7419995 (Open Web Text)

Max Activating Token Index: 881

Text #4

Max Range: 3.0541. Min Range: -3.0541

Max Act: 3.0321. Min Act: -0.1700

Data Index: 740734 (Open Web Text)

Max Activating Token Index: 458

Text #5

Max Range: 3.0541. Min Range: -3.0541

Max Act: 3.0015. Min Act: -0.1700

Data Index: 7394463 (Open Web Text)

Max Activating Token Index: 35

Text #6

Max Range: 3.0541. Min Range: -3.0541

Max Act: 3.0034. Min Act: -0.1700

Data Index: 2657410 (Open Web Text)

Max Activating Token Index: 316

Text #7

Max Range: 3.0541. Min Range: -3.0541

Max Act: 3.0049. Min Act: -0.1700

Data Index: 8562202 (Open Web Text)

Max Activating Token Index: 70

Text #8

Max Range: 3.0541. Min Range: -3.0541

Max Act: 3.0099. Min Act: -0.1700

Data Index: 7953174 (Open Web Text)

Max Activating Token Index: 753

Text #9

Max Range: 3.0541. Min Range: -3.0541

Max Act: 3.0046. Min Act: -0.1700

Data Index: 5224299 (Open Web Text)

Max Activating Token Index: 541

Text #10

Max Range: 3.0541. Min Range: -3.0541

Max Act: 3.0000. Min Act: -0.1700

Data Index: 586786 (Open Web Text)

Max Activating Token Index: 106

Text #11

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.9642. Min Act: -0.1700

Data Index: 783147 (Open Web Text)

Max Activating Token Index: 176

Text #12

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.9965. Min Act: -0.1700

Data Index: 2645518 (Open Web Text)

Max Activating Token Index: 918

Text #13

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.9748. Min Act: -0.1700

Data Index: 7100891 (Open Web Text)

Max Activating Token Index: 457

Text #14

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.9771. Min Act: -0.1700

Data Index: 3457596 (Open Web Text)

Max Activating Token Index: 23

Text #15

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.9937. Min Act: -0.1700

Data Index: 1321575 (Open Web Text)

Max Activating Token Index: 417

Text #16

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.9841. Min Act: -0.1700

Data Index: 2160104 (Open Web Text)

Max Activating Token Index: 556

Text #17

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.9772. Min Act: -0.1700

Data Index: 54290 (Open Web Text)

Max Activating Token Index: 77

Text #18

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.9620. Min Act: -0.1700

Data Index: 3739986 (Open Web Text)

Max Activating Token Index: 146

Text #19

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.9734. Min Act: -0.1700

Data Index: 2815773 (Open Web Text)

Max Activating Token Index: 393