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

Dataset: Open Web Text

Neuron 1456 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: 4.8173. Min Range: -4.8173

Max Act: 4.8173. Min Act: -0.1700

Data Index: 1112769 (Open Web Text)

Max Activating Token Index: 508

Text #1

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.8172. Min Act: -0.1700

Data Index: 5074877 (Open Web Text)

Max Activating Token Index: 473

Text #2

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.7532. Min Act: -0.1700

Data Index: 6876115 (Open Web Text)

Max Activating Token Index: 464

Text #3

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.7505. Min Act: -0.1700

Data Index: 1234610 (Open Web Text)

Max Activating Token Index: 88

Text #4

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.7494. Min Act: -0.1700

Data Index: 5245183 (Open Web Text)

Max Activating Token Index: 472

Text #5

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.7626. Min Act: -0.1700

Data Index: 3272357 (Open Web Text)

Max Activating Token Index: 768

Text #6

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.7123. Min Act: -0.1700

Data Index: 2619740 (Open Web Text)

Max Activating Token Index: 445

Text #7

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.6753. Min Act: -0.1700

Data Index: 7212209 (Open Web Text)

Max Activating Token Index: 629

Text #8

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.6818. Min Act: -0.1700

Data Index: 997872 (Open Web Text)

Max Activating Token Index: 495

Text #9

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.6705. Min Act: -0.1700

Data Index: 1923412 (Open Web Text)

Max Activating Token Index: 685

Text #10

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.6753. Min Act: -0.1700

Data Index: 3513108 (Open Web Text)

Max Activating Token Index: 724

Text #11

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.6697. Min Act: -0.1700

Data Index: 5492625 (Open Web Text)

Max Activating Token Index: 550

Text #12

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.6574. Min Act: -0.1700

Data Index: 8250580 (Open Web Text)

Max Activating Token Index: 516

Text #13

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.6296. Min Act: -0.1700

Data Index: 1746954 (Open Web Text)

Max Activating Token Index: 706

Text #14

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.6341. Min Act: -0.1700

Data Index: 6414725 (Open Web Text)

Max Activating Token Index: 628

Text #15

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.6760. Min Act: -0.1700

Data Index: 5987284 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.6550. Min Act: -0.1700

Data Index: 5900138 (Open Web Text)

Max Activating Token Index: 731

Text #17

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.6507. Min Act: -0.1700

Data Index: 2069696 (Open Web Text)

Max Activating Token Index: 83

Text #18

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.6116. Min Act: -0.1700

Data Index: 7322561 (Open Web Text)

Max Activating Token Index: 601

Text #19

Max Range: 4.8173. Min Range: -4.8173

Max Act: 4.6586. Min Act: -0.1700

Data Index: 7423898 (Open Web Text)

Max Activating Token Index: 346