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

Dataset: Open Web Text

Neuron 133 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: 4.7761. Min Range: -4.7761

Max Act: 4.7761. Min Act: -0.1700

Data Index: 1678636 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.6730. Min Act: -0.1700

Data Index: 5542371 (Open Web Text)

Max Activating Token Index: 941

Text #2

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.6569. Min Act: -0.1700

Data Index: 6021214 (Open Web Text)

Max Activating Token Index: 951

Text #3

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.6189. Min Act: -0.1700

Data Index: 4412189 (Open Web Text)

Max Activating Token Index: 889

Text #4

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.5443. Min Act: -0.1700

Data Index: 3145009 (Open Web Text)

Max Activating Token Index: 958

Text #5

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.5263. Min Act: -0.1700

Data Index: 1301796 (Open Web Text)

Max Activating Token Index: 802

Text #6

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.5249. Min Act: -0.1700

Data Index: 4602311 (Open Web Text)

Max Activating Token Index: 331

Text #7

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.4470. Min Act: -0.1700

Data Index: 5282738 (Open Web Text)

Max Activating Token Index: 821

Text #8

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.4580. Min Act: -0.1700

Data Index: 7415059 (Open Web Text)

Max Activating Token Index: 818

Text #9

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.4476. Min Act: -0.1700

Data Index: 3854459 (Open Web Text)

Max Activating Token Index: 107

Text #10

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.4510. Min Act: -0.1700

Data Index: 4362269 (Open Web Text)

Max Activating Token Index: 789

Text #11

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.4239. Min Act: -0.1700

Data Index: 7258889 (Open Web Text)

Max Activating Token Index: 815

Text #12

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.4351. Min Act: -0.1700

Data Index: 5483365 (Open Web Text)

Max Activating Token Index: 772

Text #13

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.3926. Min Act: -0.1700

Data Index: 6540482 (Open Web Text)

Max Activating Token Index: 546

Text #14

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.4172. Min Act: -0.1700

Data Index: 5614069 (Open Web Text)

Max Activating Token Index: 905

Text #15

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.4096. Min Act: -0.1700

Data Index: 6725773 (Open Web Text)

Max Activating Token Index: 792

Text #16

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.3946. Min Act: -0.1700

Data Index: 3305408 (Open Web Text)

Max Activating Token Index: 791

Text #17

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.3824. Min Act: -0.1700

Data Index: 4285690 (Open Web Text)

Max Activating Token Index: 414

Text #18

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.3681. Min Act: -0.1700

Data Index: 685428 (Open Web Text)

Max Activating Token Index: 378

Text #19

Max Range: 4.7761. Min Range: -4.7761

Max Act: 4.3915. Min Act: -0.1700

Data Index: 4707982 (Open Web Text)

Max Activating Token Index: 688