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

Dataset: Open Web Text

Neuron 803 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: 2.6757. Min Range: -2.6757

Max Act: 2.6757. Min Act: -0.1700

Data Index: 7481768 (Open Web Text)

Max Activating Token Index: 770

Text #1

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.6635. Min Act: -0.1700

Data Index: 592310 (Open Web Text)

Max Activating Token Index: 357

Text #2

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.6510. Min Act: -0.1700

Data Index: 2141967 (Open Web Text)

Max Activating Token Index: 760

Text #3

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.6180. Min Act: -0.1700

Data Index: 6637230 (Open Web Text)

Max Activating Token Index: 175

Text #4

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.6084. Min Act: -0.1700

Data Index: 8156990 (Open Web Text)

Max Activating Token Index: 566

Text #5

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5775. Min Act: -0.1700

Data Index: 631651 (Open Web Text)

Max Activating Token Index: 866

Text #6

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5919. Min Act: -0.1700

Data Index: 6626088 (Open Web Text)

Max Activating Token Index: 873

Text #7

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5827. Min Act: -0.1700

Data Index: 4385755 (Open Web Text)

Max Activating Token Index: 23

Text #8

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5841. Min Act: -0.1700

Data Index: 8562454 (Open Web Text)

Max Activating Token Index: 963

Text #9

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5683. Min Act: -0.1700

Data Index: 6920993 (Open Web Text)

Max Activating Token Index: 666

Text #10

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5595. Min Act: -0.1700

Data Index: 2537633 (Open Web Text)

Max Activating Token Index: 827

Text #11

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5392. Min Act: -0.1700

Data Index: 1988321 (Open Web Text)

Max Activating Token Index: 707

Text #12

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5431. Min Act: -0.1700

Data Index: 7720255 (Open Web Text)

Max Activating Token Index: 184

Text #13

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5551. Min Act: -0.1700

Data Index: 4040435 (Open Web Text)

Max Activating Token Index: 533

Text #14

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5401. Min Act: -0.1700

Data Index: 3326704 (Open Web Text)

Max Activating Token Index: 197

Text #15

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5286. Min Act: -0.1700

Data Index: 1304293 (Open Web Text)

Max Activating Token Index: 102

Text #16

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5203. Min Act: -0.1700

Data Index: 8222300 (Open Web Text)

Max Activating Token Index: 515

Text #17

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5325. Min Act: -0.1700

Data Index: 1904057 (Open Web Text)

Max Activating Token Index: 485

Text #18

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5101. Min Act: -0.1700

Data Index: 105483 (Open Web Text)

Max Activating Token Index: 932

Text #19

Max Range: 2.6757. Min Range: -2.6757

Max Act: 2.5102. Min Act: -0.1700

Data Index: 5444793 (Open Web Text)

Max Activating Token Index: 515