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

Dataset: Open Web Text

Neuron 2667 in Layer 5

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: 3.5617. Min Range: -3.5617

Max Act: 3.5524. Min Act: -0.1700

Data Index: 5749059 (Open Web Text)

Max Activating Token Index: 528

Text #1

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.5617. Min Act: -0.1700

Data Index: 3382369 (Open Web Text)

Max Activating Token Index: 786

Text #2

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.4883. Min Act: -0.1700

Data Index: 1510912 (Open Web Text)

Max Activating Token Index: 218

Text #3

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.4791. Min Act: -0.1700

Data Index: 4480062 (Open Web Text)

Max Activating Token Index: 112

Text #4

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.4581. Min Act: -0.1700

Data Index: 175648 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.4409. Min Act: -0.1700

Data Index: 166910 (Open Web Text)

Max Activating Token Index: 55

Text #6

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.4261. Min Act: -0.1700

Data Index: 1938455 (Open Web Text)

Max Activating Token Index: 384

Text #7

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.4259. Min Act: -0.1700

Data Index: 5947551 (Open Web Text)

Max Activating Token Index: 385

Text #8

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.3909. Min Act: -0.1700

Data Index: 4205147 (Open Web Text)

Max Activating Token Index: 466

Text #9

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.4145. Min Act: -0.1700

Data Index: 3434633 (Open Web Text)

Max Activating Token Index: 847

Text #10

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.4459. Min Act: -0.1700

Data Index: 6513281 (Open Web Text)

Max Activating Token Index: 644

Text #11

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.4137. Min Act: -0.1700

Data Index: 8832673 (Open Web Text)

Max Activating Token Index: 256

Text #12

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.4481. Min Act: -0.1700

Data Index: 2817390 (Open Web Text)

Max Activating Token Index: 453

Text #13

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.4115. Min Act: -0.1700

Data Index: 4118018 (Open Web Text)

Max Activating Token Index: 817

Text #14

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.4023. Min Act: -0.1700

Data Index: 2610559 (Open Web Text)

Max Activating Token Index: 113

Text #15

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.4055. Min Act: -0.1700

Data Index: 3690928 (Open Web Text)

Max Activating Token Index: 775

Text #16

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.3603. Min Act: -0.1700

Data Index: 3764536 (Open Web Text)

Max Activating Token Index: 399

Text #17

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.3447. Min Act: -0.1700

Data Index: 8585955 (Open Web Text)

Max Activating Token Index: 487

Text #18

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.3626. Min Act: -0.1700

Data Index: 4389384 (Open Web Text)

Max Activating Token Index: 760

Text #19

Max Range: 3.5617. Min Range: -3.5617

Max Act: 3.3752. Min Act: -0.1700

Data Index: 3879074 (Open Web Text)

Max Activating Token Index: 411