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

Dataset: Open Web Text

Neuron 2529 in Layer 6

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: 3.1673. Min Range: -3.1673

Max Act: 3.1673. Min Act: -0.1700

Data Index: 4237258 (Open Web Text)

Max Activating Token Index: 907

Text #1

Max Range: 3.1673. Min Range: -3.1673

Max Act: 3.0201. Min Act: -0.1700

Data Index: 4464452 (Open Web Text)

Max Activating Token Index: 736

Text #2

Max Range: 3.1673. Min Range: -3.1673

Max Act: 3.0110. Min Act: -0.1700

Data Index: 706551 (Open Web Text)

Max Activating Token Index: 89

Text #3

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9599. Min Act: -0.1700

Data Index: 425549 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9435. Min Act: -0.1700

Data Index: 7580515 (Open Web Text)

Max Activating Token Index: 992

Text #5

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9351. Min Act: -0.1700

Data Index: 1541216 (Open Web Text)

Max Activating Token Index: 626

Text #6

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9040. Min Act: -0.1700

Data Index: 5857706 (Open Web Text)

Max Activating Token Index: 812

Text #7

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9296. Min Act: -0.1700

Data Index: 1250868 (Open Web Text)

Max Activating Token Index: 952

Text #8

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9088. Min Act: -0.1700

Data Index: 6865764 (Open Web Text)

Max Activating Token Index: 374

Text #9

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.8965. Min Act: -0.1700

Data Index: 5334197 (Open Web Text)

Max Activating Token Index: 416

Text #10

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.8848. Min Act: -0.1700

Data Index: 3588215 (Open Web Text)

Max Activating Token Index: 491

Text #11

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.8531. Min Act: -0.1700

Data Index: 4406215 (Open Web Text)

Max Activating Token Index: 455

Text #12

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.8936. Min Act: -0.1700

Data Index: 8729222 (Open Web Text)

Max Activating Token Index: 507

Text #13

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.8841. Min Act: -0.1700

Data Index: 5150116 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.8708. Min Act: -0.1700

Data Index: 5935523 (Open Web Text)

Max Activating Token Index: 519

Text #15

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.8750. Min Act: -0.1700

Data Index: 7762953 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.8497. Min Act: -0.1700

Data Index: 8002447 (Open Web Text)

Max Activating Token Index: 972

Text #17

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.8701. Min Act: -0.1700

Data Index: 986325 (Open Web Text)

Max Activating Token Index: 783

Text #18

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.8618. Min Act: -0.1700

Data Index: 6664615 (Open Web Text)

Max Activating Token Index: 329

Text #19

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.8371. Min Act: -0.1700

Data Index: 3589502 (Open Web Text)

Max Activating Token Index: 986