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

Dataset: Open Web Text

Neuron 75 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: 4.0687. Min Range: -4.0687

Max Act: 4.0687. Min Act: -0.1700

Data Index: 312472 (Open Web Text)

Max Activating Token Index: 595

Text #1

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.9455. Min Act: -0.1700

Data Index: 7574231 (Open Web Text)

Max Activating Token Index: 963

Text #2

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.8438. Min Act: -0.1700

Data Index: 6097282 (Open Web Text)

Max Activating Token Index: 882

Text #3

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.7699. Min Act: -0.1700

Data Index: 5331127 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.7455. Min Act: -0.1700

Data Index: 8543415 (Open Web Text)

Max Activating Token Index: 733

Text #5

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.7379. Min Act: -0.1700

Data Index: 1623252 (Open Web Text)

Max Activating Token Index: 478

Text #6

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.6976. Min Act: -0.1700

Data Index: 854350 (Open Web Text)

Max Activating Token Index: 860

Text #7

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.6623. Min Act: -0.1700

Data Index: 1499940 (Open Web Text)

Max Activating Token Index: 741

Text #8

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.6452. Min Act: -0.1700

Data Index: 806839 (Open Web Text)

Max Activating Token Index: 28

Text #9

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.6516. Min Act: -0.1700

Data Index: 2240996 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.6173. Min Act: -0.1700

Data Index: 1731730 (Open Web Text)

Max Activating Token Index: 796

Text #11

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.6667. Min Act: -0.1700

Data Index: 8710716 (Open Web Text)

Max Activating Token Index: 359

Text #12

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.6452. Min Act: -0.1700

Data Index: 7224588 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.6795. Min Act: -0.1700

Data Index: 5588703 (Open Web Text)

Max Activating Token Index: 570

Text #14

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.5972. Min Act: -0.1700

Data Index: 427994 (Open Web Text)

Max Activating Token Index: 38

Text #15

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.6058. Min Act: -0.1700

Data Index: 4215580 (Open Web Text)

Max Activating Token Index: 782

Text #16

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.5906. Min Act: -0.1700

Data Index: 8069764 (Open Web Text)

Max Activating Token Index: 1013

Text #17

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.5772. Min Act: -0.1700

Data Index: 7976058 (Open Web Text)

Max Activating Token Index: 639

Text #18

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.5960. Min Act: -0.1700

Data Index: 6159064 (Open Web Text)

Max Activating Token Index: 981

Text #19

Max Range: 4.0687. Min Range: -4.0687

Max Act: 3.5876. Min Act: -0.1700

Data Index: 4529736 (Open Web Text)

Max Activating Token Index: 319