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

Dataset: Open Web Text

Neuron 1789 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: 4.0123. Min Range: -4.0123

Max Act: 3.9806. Min Act: -0.1700

Data Index: 282671 (Open Web Text)

Max Activating Token Index: 382

Text #1

Max Range: 4.0123. Min Range: -4.0123

Max Act: 4.0123. Min Act: -0.1700

Data Index: 3982037 (Open Web Text)

Max Activating Token Index: 117

Text #2

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.9592. Min Act: -0.1700

Data Index: 3813964 (Open Web Text)

Max Activating Token Index: 144

Text #3

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.9024. Min Act: -0.1700

Data Index: 1736373 (Open Web Text)

Max Activating Token Index: 943

Text #4

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.8534. Min Act: -0.1700

Data Index: 7040637 (Open Web Text)

Max Activating Token Index: 106

Text #5

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.8337. Min Act: -0.1700

Data Index: 22120 (Open Web Text)

Max Activating Token Index: 619

Text #6

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.8051. Min Act: -0.1700

Data Index: 2544277 (Open Web Text)

Max Activating Token Index: 608

Text #7

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.8296. Min Act: -0.1700

Data Index: 6051946 (Open Web Text)

Max Activating Token Index: 63

Text #8

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7729. Min Act: -0.1700

Data Index: 5838136 (Open Web Text)

Max Activating Token Index: 657

Text #9

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7798. Min Act: -0.1700

Data Index: 919703 (Open Web Text)

Max Activating Token Index: 69

Text #10

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.8004. Min Act: -0.1700

Data Index: 6768958 (Open Web Text)

Max Activating Token Index: 573

Text #11

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7646. Min Act: -0.1700

Data Index: 3918521 (Open Web Text)

Max Activating Token Index: 136

Text #12

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7379. Min Act: -0.1700

Data Index: 507577 (Open Web Text)

Max Activating Token Index: 555

Text #13

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7589. Min Act: -0.1700

Data Index: 7938734 (Open Web Text)

Max Activating Token Index: 866

Text #14

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7420. Min Act: -0.1700

Data Index: 1347319 (Open Web Text)

Max Activating Token Index: 654

Text #15

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7295. Min Act: -0.1700

Data Index: 7911265 (Open Web Text)

Max Activating Token Index: 655

Text #16

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.6969. Min Act: -0.1700

Data Index: 2542703 (Open Web Text)

Max Activating Token Index: 913

Text #17

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7171. Min Act: -0.1700

Data Index: 1157269 (Open Web Text)

Max Activating Token Index: 329

Text #18

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7282. Min Act: -0.1700

Data Index: 2193766 (Open Web Text)

Max Activating Token Index: 617

Text #19

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7229. Min Act: -0.1700

Data Index: 558481 (Open Web Text)

Max Activating Token Index: 875