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

Dataset: Open Web Text

Neuron 1898 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: 4.2959. Min Range: -4.2959

Max Act: 4.2959. Min Act: -0.1700

Data Index: 1012658 (Open Web Text)

Max Activating Token Index: 505

Text #1

Max Range: 4.2959. Min Range: -4.2959

Max Act: 4.2242. Min Act: -0.1700

Data Index: 2728489 (Open Web Text)

Max Activating Token Index: 831

Text #2

Max Range: 4.2959. Min Range: -4.2959

Max Act: 4.2484. Min Act: -0.1700

Data Index: 7814186 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 4.2959. Min Range: -4.2959

Max Act: 4.2227. Min Act: -0.1700

Data Index: 7581017 (Open Web Text)

Max Activating Token Index: 137

Text #4

Max Range: 4.2959. Min Range: -4.2959

Max Act: 4.1638. Min Act: -0.1700

Data Index: 5862967 (Open Web Text)

Max Activating Token Index: 676

Text #5

Max Range: 4.2959. Min Range: -4.2959

Max Act: 4.0896. Min Act: -0.1700

Data Index: 7203443 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.2959. Min Range: -4.2959

Max Act: 4.1094. Min Act: -0.1700

Data Index: 1154051 (Open Web Text)

Max Activating Token Index: 595

Text #7

Max Range: 4.2959. Min Range: -4.2959

Max Act: 4.0866. Min Act: -0.1700

Data Index: 7225839 (Open Web Text)

Max Activating Token Index: 463

Text #8

Max Range: 4.2959. Min Range: -4.2959

Max Act: 4.0133. Min Act: -0.1700

Data Index: 6735098 (Open Web Text)

Max Activating Token Index: 585

Text #9

Max Range: 4.2959. Min Range: -4.2959

Max Act: 4.0466. Min Act: -0.1700

Data Index: 7287109 (Open Web Text)

Max Activating Token Index: 721

Text #10

Max Range: 4.2959. Min Range: -4.2959

Max Act: 4.0468. Min Act: -0.1700

Data Index: 3697394 (Open Web Text)

Max Activating Token Index: 829

Text #11

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.9921. Min Act: -0.1700

Data Index: 7338344 (Open Web Text)

Max Activating Token Index: 482

Text #12

Max Range: 4.2959. Min Range: -4.2959

Max Act: 4.0008. Min Act: -0.1700

Data Index: 2458778 (Open Web Text)

Max Activating Token Index: 49

Text #13

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.9833. Min Act: -0.1700

Data Index: 2378024 (Open Web Text)

Max Activating Token Index: 233

Text #14

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.9704. Min Act: -0.1700

Data Index: 4485915 (Open Web Text)

Max Activating Token Index: 782

Text #15

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.9880. Min Act: -0.1700

Data Index: 1001170 (Open Web Text)

Max Activating Token Index: 437

Text #16

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.9864. Min Act: -0.1700

Data Index: 6328737 (Open Web Text)

Max Activating Token Index: 80

Text #17

Max Range: 4.2959. Min Range: -4.2959

Max Act: 4.0184. Min Act: -0.1700

Data Index: 5067314 (Open Web Text)

Max Activating Token Index: 817

Text #18

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.9849. Min Act: -0.1700

Data Index: 4796020 (Open Web Text)

Max Activating Token Index: 696

Text #19

Max Range: 4.2959. Min Range: -4.2959

Max Act: 3.9839. Min Act: -0.1700

Data Index: 7040351 (Open Web Text)

Max Activating Token Index: 290