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

Dataset: Open Web Text

Neuron 2271 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: 1.8797. Min Range: -1.8797

Max Act: 1.8797. Min Act: -0.1700

Data Index: 2427802 (Open Web Text)

Max Activating Token Index: 72

Text #1

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.8503. Min Act: -0.1700

Data Index: 7462194 (Open Web Text)

Max Activating Token Index: 555

Text #2

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.8331. Min Act: -0.1700

Data Index: 7045223 (Open Web Text)

Max Activating Token Index: 245

Text #3

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.8261. Min Act: -0.1700

Data Index: 1120447 (Open Web Text)

Max Activating Token Index: 126

Text #4

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.8118. Min Act: -0.1700

Data Index: 366229 (Open Web Text)

Max Activating Token Index: 794

Text #5

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.8152. Min Act: -0.1700

Data Index: 853305 (Open Web Text)

Max Activating Token Index: 954

Text #6

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.8092. Min Act: -0.1700

Data Index: 7170315 (Open Web Text)

Max Activating Token Index: 211

Text #7

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.7933. Min Act: -0.1700

Data Index: 2513531 (Open Web Text)

Max Activating Token Index: 770

Text #8

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.8073. Min Act: -0.1700

Data Index: 5098539 (Open Web Text)

Max Activating Token Index: 312

Text #9

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.7989. Min Act: -0.1700

Data Index: 893228 (Open Web Text)

Max Activating Token Index: 530

Text #10

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.7929. Min Act: -0.1700

Data Index: 2682053 (Open Web Text)

Max Activating Token Index: 317

Text #11

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.7969. Min Act: -0.1700

Data Index: 4220776 (Open Web Text)

Max Activating Token Index: 72

Text #12

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.7957. Min Act: -0.1700

Data Index: 4790959 (Open Web Text)

Max Activating Token Index: 52

Text #13

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.7721. Min Act: -0.1700

Data Index: 5993930 (Open Web Text)

Max Activating Token Index: 471

Text #14

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.7659. Min Act: -0.1700

Data Index: 644852 (Open Web Text)

Max Activating Token Index: 940

Text #15

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.8011. Min Act: -0.1700

Data Index: 8798025 (Open Web Text)

Max Activating Token Index: 765

Text #16

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.7769. Min Act: -0.1700

Data Index: 664533 (Open Web Text)

Max Activating Token Index: 849

Text #17

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.7872. Min Act: -0.1700

Data Index: 1506144 (Open Web Text)

Max Activating Token Index: 334

Text #18

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.7675. Min Act: -0.1700

Data Index: 7620950 (Open Web Text)

Max Activating Token Index: 664

Text #19

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.7696. Min Act: -0.1700

Data Index: 7691772 (Open Web Text)

Max Activating Token Index: 631