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

Dataset: Open Web Text

Neuron 87 in Layer 1

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: 5.0104. Min Range: -5.0104

Max Act: 5.0104. Min Act: -0.1700

Data Index: 8773577 (Open Web Text)

Max Activating Token Index: 484

Text #1

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8853. Min Act: -0.1700

Data Index: 1729124 (Open Web Text)

Max Activating Token Index: 58

Text #2

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.9250. Min Act: -0.1700

Data Index: 3976146 (Open Web Text)

Max Activating Token Index: 305

Text #3

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8881. Min Act: -0.1700

Data Index: 4092371 (Open Web Text)

Max Activating Token Index: 394

Text #4

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8743. Min Act: -0.1700

Data Index: 3032233 (Open Web Text)

Max Activating Token Index: 611

Text #5

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8774. Min Act: -0.1700

Data Index: 7088605 (Open Web Text)

Max Activating Token Index: 358

Text #6

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8903. Min Act: -0.1700

Data Index: 6183797 (Open Web Text)

Max Activating Token Index: 494

Text #7

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.9066. Min Act: -0.1700

Data Index: 6296443 (Open Web Text)

Max Activating Token Index: 565

Text #8

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8933. Min Act: -0.1700

Data Index: 1346381 (Open Web Text)

Max Activating Token Index: 379

Text #9

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8671. Min Act: -0.1700

Data Index: 604670 (Open Web Text)

Max Activating Token Index: 545

Text #10

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8536. Min Act: -0.1700

Data Index: 3254307 (Open Web Text)

Max Activating Token Index: 130

Text #11

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8718. Min Act: -0.1700

Data Index: 7799228 (Open Web Text)

Max Activating Token Index: 494

Text #12

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8608. Min Act: -0.1700

Data Index: 6183795 (Open Web Text)

Max Activating Token Index: 517

Text #13

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8520. Min Act: -0.1700

Data Index: 3586054 (Open Web Text)

Max Activating Token Index: 639

Text #14

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8515. Min Act: -0.1700

Data Index: 4713460 (Open Web Text)

Max Activating Token Index: 479

Text #15

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8657. Min Act: -0.1700

Data Index: 2772976 (Open Web Text)

Max Activating Token Index: 598

Text #16

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8716. Min Act: -0.1700

Data Index: 994914 (Open Web Text)

Max Activating Token Index: 53

Text #17

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8661. Min Act: -0.1700

Data Index: 845002 (Open Web Text)

Max Activating Token Index: 442

Text #18

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8517. Min Act: -0.1700

Data Index: 467051 (Open Web Text)

Max Activating Token Index: 644

Text #19

Max Range: 5.0104. Min Range: -5.0104

Max Act: 4.8273. Min Act: -0.1700

Data Index: 3478630 (Open Web Text)

Max Activating Token Index: 40