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

Dataset: Open Web Text

Neuron 1852 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: 2.1066. Min Range: -2.1066

Max Act: 2.1066. Min Act: -0.1700

Data Index: 8264479 (Open Web Text)

Max Activating Token Index: 273

Text #1

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.0433. Min Act: -0.1700

Data Index: 434796 (Open Web Text)

Max Activating Token Index: 159

Text #2

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.0644. Min Act: -0.1700

Data Index: 6048883 (Open Web Text)

Max Activating Token Index: 700

Text #3

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.0251. Min Act: -0.1700

Data Index: 1053695 (Open Web Text)

Max Activating Token Index: 673

Text #4

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.0306. Min Act: -0.1700

Data Index: 1542513 (Open Web Text)

Max Activating Token Index: 731

Text #5

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.0305. Min Act: -0.1700

Data Index: 293481 (Open Web Text)

Max Activating Token Index: 633

Text #6

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.0062. Min Act: -0.1700

Data Index: 8218726 (Open Web Text)

Max Activating Token Index: 628

Text #7

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.0050. Min Act: -0.1700

Data Index: 2224971 (Open Web Text)

Max Activating Token Index: 759

Text #8

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.0303. Min Act: -0.1700

Data Index: 5401590 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.0215. Min Act: -0.1700

Data Index: 2159874 (Open Web Text)

Max Activating Token Index: 288

Text #10

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.0313. Min Act: -0.1700

Data Index: 6499110 (Open Web Text)

Max Activating Token Index: 781

Text #11

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.0092. Min Act: -0.1700

Data Index: 3599686 (Open Web Text)

Max Activating Token Index: 797

Text #12

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.0042. Min Act: -0.1700

Data Index: 5789076 (Open Web Text)

Max Activating Token Index: 560

Text #13

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.0089. Min Act: -0.1700

Data Index: 295989 (Open Web Text)

Max Activating Token Index: 994

Text #14

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.0140. Min Act: -0.1700

Data Index: 2839123 (Open Web Text)

Max Activating Token Index: 1021

Text #15

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.9948. Min Act: -0.1700

Data Index: 882095 (Open Web Text)

Max Activating Token Index: 817

Text #16

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.9812. Min Act: -0.1700

Data Index: 373767 (Open Web Text)

Max Activating Token Index: 531

Text #17

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.9803. Min Act: -0.1700

Data Index: 2709308 (Open Web Text)

Max Activating Token Index: 1009

Text #18

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.9872. Min Act: -0.1700

Data Index: 6244210 (Open Web Text)

Max Activating Token Index: 421

Text #19

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.9874. Min Act: -0.1700

Data Index: 6431251 (Open Web Text)

Max Activating Token Index: 670