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

Dataset: Open Web Text

Neuron 419 in Layer 5

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: 7.0786. Min Range: -7.0786

Max Act: 7.0786. Min Act: -0.1697

Data Index: 4535355 (Open Web Text)

Max Activating Token Index: 918

Text #1

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.9425. Min Act: -0.1692

Data Index: 1444266 (Open Web Text)

Max Activating Token Index: 739

Text #2

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.9615. Min Act: -0.1700

Data Index: 8496856 (Open Web Text)

Max Activating Token Index: 65

Text #3

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.9377. Min Act: -0.1698

Data Index: 6115612 (Open Web Text)

Max Activating Token Index: 894

Text #4

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.8961. Min Act: -0.1700

Data Index: 6269356 (Open Web Text)

Max Activating Token Index: 440

Text #5

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.8753. Min Act: -0.1700

Data Index: 3423251 (Open Web Text)

Max Activating Token Index: 607

Text #6

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.8312. Min Act: -0.1700

Data Index: 8504175 (Open Web Text)

Max Activating Token Index: 934

Text #7

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.8441. Min Act: -0.1697

Data Index: 5424798 (Open Web Text)

Max Activating Token Index: 452

Text #8

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.8507. Min Act: -0.1698

Data Index: 6325780 (Open Web Text)

Max Activating Token Index: 347

Text #9

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.8338. Min Act: -0.1700

Data Index: 8659990 (Open Web Text)

Max Activating Token Index: 968

Text #10

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.7810. Min Act: -0.1700

Data Index: 7998368 (Open Web Text)

Max Activating Token Index: 608

Text #11

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.7352. Min Act: -0.1700

Data Index: 488933 (Open Web Text)

Max Activating Token Index: 179

Text #12

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.7719. Min Act: -0.1700

Data Index: 4419052 (Open Web Text)

Max Activating Token Index: 89

Text #13

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.7349. Min Act: -0.1700

Data Index: 2957821 (Open Web Text)

Max Activating Token Index: 453

Text #14

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.7418. Min Act: -0.1699

Data Index: 2863127 (Open Web Text)

Max Activating Token Index: 471

Text #15

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.7017. Min Act: -0.1700

Data Index: 4411172 (Open Web Text)

Max Activating Token Index: 186

Text #16

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.6945. Min Act: -0.1700

Data Index: 5499650 (Open Web Text)

Max Activating Token Index: 224

Text #17

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.6352. Min Act: -0.1699

Data Index: 1830612 (Open Web Text)

Max Activating Token Index: 539

Text #18

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.6771. Min Act: -0.1700

Data Index: 4653453 (Open Web Text)

Max Activating Token Index: 726

Text #19

Max Range: 7.0786. Min Range: -7.0786

Max Act: 6.6340. Min Act: -0.1699

Data Index: 6124313 (Open Web Text)

Max Activating Token Index: 1020