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

Dataset: Open Web Text

Neuron 1725 in Layer 3

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: 4.0797. Min Range: -4.0797

Max Act: 4.0797. Min Act: -0.1700

Data Index: 1160708 (Open Web Text)

Max Activating Token Index: 671

Text #1

Max Range: 4.0797. Min Range: -4.0797

Max Act: 4.0462. Min Act: -0.1700

Data Index: 8044829 (Open Web Text)

Max Activating Token Index: 182

Text #2

Max Range: 4.0797. Min Range: -4.0797

Max Act: 4.0378. Min Act: -0.1700

Data Index: 3338699 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.0797. Min Range: -4.0797

Max Act: 4.0539. Min Act: -0.1700

Data Index: 8361050 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 4.0797. Min Range: -4.0797

Max Act: 4.0786. Min Act: -0.1700

Data Index: 2146155 (Open Web Text)

Max Activating Token Index: 556

Text #5

Max Range: 4.0797. Min Range: -4.0797

Max Act: 4.0515. Min Act: -0.1700

Data Index: 2196381 (Open Web Text)

Max Activating Token Index: 845

Text #6

Max Range: 4.0797. Min Range: -4.0797

Max Act: 4.0539. Min Act: -0.1700

Data Index: 318927 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.0797. Min Range: -4.0797

Max Act: 4.0587. Min Act: -0.1700

Data Index: 84392 (Open Web Text)

Max Activating Token Index: 90

Text #8

Max Range: 4.0797. Min Range: -4.0797

Max Act: 4.0193. Min Act: -0.1700

Data Index: 8207621 (Open Web Text)

Max Activating Token Index: 625

Text #9

Max Range: 4.0797. Min Range: -4.0797

Max Act: 4.0358. Min Act: -0.1700

Data Index: 6580046 (Open Web Text)

Max Activating Token Index: 463

Text #10

Max Range: 4.0797. Min Range: -4.0797

Max Act: 3.9921. Min Act: -0.1700

Data Index: 5347615 (Open Web Text)

Max Activating Token Index: 830

Text #11

Max Range: 4.0797. Min Range: -4.0797

Max Act: 3.9655. Min Act: -0.1700

Data Index: 7018489 (Open Web Text)

Max Activating Token Index: 189

Text #12

Max Range: 4.0797. Min Range: -4.0797

Max Act: 3.9684. Min Act: -0.1700

Data Index: 7011393 (Open Web Text)

Max Activating Token Index: 488

Text #13

Max Range: 4.0797. Min Range: -4.0797

Max Act: 3.9735. Min Act: -0.1700

Data Index: 4074059 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.0797. Min Range: -4.0797

Max Act: 3.9923. Min Act: -0.1700

Data Index: 8541443 (Open Web Text)

Max Activating Token Index: 69

Text #15

Max Range: 4.0797. Min Range: -4.0797

Max Act: 3.9740. Min Act: -0.1700

Data Index: 5506278 (Open Web Text)

Max Activating Token Index: 251

Text #16

Max Range: 4.0797. Min Range: -4.0797

Max Act: 3.9953. Min Act: -0.1700

Data Index: 4986064 (Open Web Text)

Max Activating Token Index: 73

Text #17

Max Range: 4.0797. Min Range: -4.0797

Max Act: 3.9453. Min Act: -0.1700

Data Index: 4070018 (Open Web Text)

Max Activating Token Index: 787

Text #18

Max Range: 4.0797. Min Range: -4.0797

Max Act: 3.9550. Min Act: -0.1700

Data Index: 6619583 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.0797. Min Range: -4.0797

Max Act: 3.9412. Min Act: -0.1700

Data Index: 942676 (Open Web Text)

Max Activating Token Index: 864