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

Dataset: Open Web Text

Neuron 2518 in Layer 6

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: 3.0619. Min Range: -3.0619

Max Act: 3.0619. Min Act: -0.1700

Data Index: 7047330 (Open Web Text)

Max Activating Token Index: 692

Text #1

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.9744. Min Act: -0.1700

Data Index: 2840451 (Open Web Text)

Max Activating Token Index: 166

Text #2

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.9062. Min Act: -0.1700

Data Index: 3759746 (Open Web Text)

Max Activating Token Index: 536

Text #3

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.8604. Min Act: -0.1700

Data Index: 4642111 (Open Web Text)

Max Activating Token Index: 668

Text #4

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.8525. Min Act: -0.1700

Data Index: 8413736 (Open Web Text)

Max Activating Token Index: 369

Text #5

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.8569. Min Act: -0.1700

Data Index: 4754948 (Open Web Text)

Max Activating Token Index: 583

Text #6

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.8365. Min Act: -0.1700

Data Index: 7091594 (Open Web Text)

Max Activating Token Index: 749

Text #7

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.8348. Min Act: -0.1700

Data Index: 5700704 (Open Web Text)

Max Activating Token Index: 137

Text #8

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.8403. Min Act: -0.1700

Data Index: 1316856 (Open Web Text)

Max Activating Token Index: 341

Text #9

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.8453. Min Act: -0.1700

Data Index: 5161820 (Open Web Text)

Max Activating Token Index: 530

Text #10

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.8452. Min Act: -0.1700

Data Index: 3053723 (Open Web Text)

Max Activating Token Index: 378

Text #11

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.8177. Min Act: -0.1700

Data Index: 5323746 (Open Web Text)

Max Activating Token Index: 845

Text #12

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.8277. Min Act: -0.1700

Data Index: 3107266 (Open Web Text)

Max Activating Token Index: 91

Text #13

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.8267. Min Act: -0.1700

Data Index: 1766933 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.8387. Min Act: -0.1700

Data Index: 7235795 (Open Web Text)

Max Activating Token Index: 635

Text #15

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.8229. Min Act: -0.1700

Data Index: 7246397 (Open Web Text)

Max Activating Token Index: 180

Text #16

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.8169. Min Act: -0.1700

Data Index: 1503016 (Open Web Text)

Max Activating Token Index: 107

Text #17

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.7924. Min Act: -0.1700

Data Index: 8277382 (Open Web Text)

Max Activating Token Index: 691

Text #18

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.7912. Min Act: -0.1700

Data Index: 2426628 (Open Web Text)

Max Activating Token Index: 608

Text #19

Max Range: 3.0619. Min Range: -3.0619

Max Act: 2.7767. Min Act: -0.1700

Data Index: 4422042 (Open Web Text)

Max Activating Token Index: 738