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

Dataset: Open Web Text

Neuron 796 in Layer 0

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: 4.5726. Min Range: -4.5726

Max Act: 4.5726. Min Act: -0.1700

Data Index: 6963695 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.5406. Min Act: -0.1700

Data Index: 817888 (Open Web Text)

Max Activating Token Index: 673

Text #2

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.5194. Min Act: -0.1700

Data Index: 719904 (Open Web Text)

Max Activating Token Index: 837

Text #3

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.5080. Min Act: -0.1700

Data Index: 3570140 (Open Web Text)

Max Activating Token Index: 662

Text #4

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.4744. Min Act: -0.1700

Data Index: 3852977 (Open Web Text)

Max Activating Token Index: 125

Text #5

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.4740. Min Act: -0.1700

Data Index: 2602394 (Open Web Text)

Max Activating Token Index: 512

Text #6

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.4424. Min Act: -0.1700

Data Index: 5482467 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.4422. Min Act: -0.1700

Data Index: 6930973 (Open Web Text)

Max Activating Token Index: 483

Text #8

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.4387. Min Act: -0.1700

Data Index: 2417630 (Open Web Text)

Max Activating Token Index: 205

Text #9

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.3952. Min Act: -0.1700

Data Index: 3209330 (Open Web Text)

Max Activating Token Index: 43

Text #10

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.4261. Min Act: -0.1700

Data Index: 5917742 (Open Web Text)

Max Activating Token Index: 250

Text #11

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.4297. Min Act: -0.1700

Data Index: 8237709 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.4112. Min Act: -0.1700

Data Index: 4205410 (Open Web Text)

Max Activating Token Index: 712

Text #13

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.4115. Min Act: -0.1700

Data Index: 2901808 (Open Web Text)

Max Activating Token Index: 915

Text #14

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.3826. Min Act: -0.1700

Data Index: 7869126 (Open Web Text)

Max Activating Token Index: 39

Text #15

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.3615. Min Act: -0.1700

Data Index: 7607597 (Open Web Text)

Max Activating Token Index: 350

Text #16

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.3603. Min Act: -0.1700

Data Index: 2335898 (Open Web Text)

Max Activating Token Index: 683

Text #17

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.3674. Min Act: -0.1700

Data Index: 7933001 (Open Web Text)

Max Activating Token Index: 48

Text #18

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.3617. Min Act: -0.1700

Data Index: 8644254 (Open Web Text)

Max Activating Token Index: 1007

Text #19

Max Range: 4.5726. Min Range: -4.5726

Max Act: 4.3775. Min Act: -0.1700

Data Index: 713125 (Open Web Text)

Max Activating Token Index: 812