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

Dataset: Open Web Text

Neuron 95 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: 2.0661. Min Range: -2.0661

Max Act: 2.0661. Min Act: -0.1700

Data Index: 6882255 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 2.0661. Min Range: -2.0661

Max Act: 2.0510. Min Act: -0.1700

Data Index: 7117187 (Open Web Text)

Max Activating Token Index: 241

Text #2

Max Range: 2.0661. Min Range: -2.0661

Max Act: 2.0055. Min Act: -0.1700

Data Index: 5654851 (Open Web Text)

Max Activating Token Index: 38

Text #3

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9962. Min Act: -0.1700

Data Index: 1073286 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9605. Min Act: -0.1700

Data Index: 7289714 (Open Web Text)

Max Activating Token Index: 345

Text #5

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9577. Min Act: -0.1700

Data Index: 5817648 (Open Web Text)

Max Activating Token Index: 210

Text #6

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9583. Min Act: -0.1700

Data Index: 8441022 (Open Web Text)

Max Activating Token Index: 222

Text #7

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9689. Min Act: -0.1700

Data Index: 2220699 (Open Web Text)

Max Activating Token Index: 395

Text #8

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9486. Min Act: -0.1700

Data Index: 8781442 (Open Web Text)

Max Activating Token Index: 147

Text #9

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9470. Min Act: -0.1700

Data Index: 3942720 (Open Web Text)

Max Activating Token Index: 844

Text #10

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9655. Min Act: -0.1700

Data Index: 2866941 (Open Web Text)

Max Activating Token Index: 112

Text #11

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9529. Min Act: -0.1700

Data Index: 1495593 (Open Web Text)

Max Activating Token Index: 583

Text #12

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9595. Min Act: -0.1700

Data Index: 4724495 (Open Web Text)

Max Activating Token Index: 715

Text #13

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9657. Min Act: -0.1700

Data Index: 8409255 (Open Web Text)

Max Activating Token Index: 75

Text #14

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9404. Min Act: -0.1700

Data Index: 5052460 (Open Web Text)

Max Activating Token Index: 32

Text #15

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9537. Min Act: -0.1700

Data Index: 3655228 (Open Web Text)

Max Activating Token Index: 465

Text #16

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9420. Min Act: -0.1700

Data Index: 4524333 (Open Web Text)

Max Activating Token Index: 657

Text #17

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9537. Min Act: -0.1700

Data Index: 8198243 (Open Web Text)

Max Activating Token Index: 526

Text #18

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9356. Min Act: -0.1700

Data Index: 7157288 (Open Web Text)

Max Activating Token Index: 49

Text #19

Max Range: 2.0661. Min Range: -2.0661

Max Act: 1.9605. Min Act: -0.1700

Data Index: 924661 (Open Web Text)

Max Activating Token Index: 58