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

Dataset: Open Web Text

Neuron 1905 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: 4.5704. Min Range: -4.5704

Max Act: 4.5704. Min Act: -0.1700

Data Index: 6331919 (Open Web Text)

Max Activating Token Index: 705

Text #1

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.5147. Min Act: -0.1700

Data Index: 5515492 (Open Web Text)

Max Activating Token Index: 110

Text #2

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.5167. Min Act: -0.1700

Data Index: 773718 (Open Web Text)

Max Activating Token Index: 782

Text #3

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4731. Min Act: -0.1700

Data Index: 373401 (Open Web Text)

Max Activating Token Index: 798

Text #4

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4874. Min Act: -0.1700

Data Index: 3048760 (Open Web Text)

Max Activating Token Index: 886

Text #5

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4840. Min Act: -0.1700

Data Index: 3393798 (Open Web Text)

Max Activating Token Index: 816

Text #6

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4831. Min Act: -0.1700

Data Index: 4766855 (Open Web Text)

Max Activating Token Index: 949

Text #7

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4646. Min Act: -0.1700

Data Index: 3431875 (Open Web Text)

Max Activating Token Index: 647

Text #8

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4422. Min Act: -0.1700

Data Index: 3939978 (Open Web Text)

Max Activating Token Index: 726

Text #9

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4535. Min Act: -0.1700

Data Index: 7872623 (Open Web Text)

Max Activating Token Index: 683

Text #10

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4233. Min Act: -0.1700

Data Index: 7575378 (Open Web Text)

Max Activating Token Index: 368

Text #11

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4490. Min Act: -0.1700

Data Index: 6339235 (Open Web Text)

Max Activating Token Index: 856

Text #12

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4649. Min Act: -0.1700

Data Index: 1334697 (Open Web Text)

Max Activating Token Index: 690

Text #13

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4562. Min Act: -0.1700

Data Index: 5910374 (Open Web Text)

Max Activating Token Index: 52

Text #14

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4646. Min Act: -0.1700

Data Index: 5844728 (Open Web Text)

Max Activating Token Index: 537

Text #15

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4148. Min Act: -0.1700

Data Index: 3821283 (Open Web Text)

Max Activating Token Index: 829

Text #16

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4299. Min Act: -0.1700

Data Index: 838255 (Open Web Text)

Max Activating Token Index: 801

Text #17

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4217. Min Act: -0.1700

Data Index: 3839151 (Open Web Text)

Max Activating Token Index: 891

Text #18

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4276. Min Act: -0.1700

Data Index: 1910533 (Open Web Text)

Max Activating Token Index: 755

Text #19

Max Range: 4.5704. Min Range: -4.5704

Max Act: 4.4109. Min Act: -0.1700

Data Index: 4232683 (Open Web Text)

Max Activating Token Index: 844