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

Dataset: Open Web Text

Neuron 1898 in Layer 2

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: 3.9987. Min Range: -3.9987

Max Act: 3.9933. Min Act: -0.1700

Data Index: 3344806 (Open Web Text)

Max Activating Token Index: 800

Text #1

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.9567. Min Act: -0.1700

Data Index: 8390152 (Open Web Text)

Max Activating Token Index: 190

Text #2

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.9987. Min Act: -0.1700

Data Index: 4407600 (Open Web Text)

Max Activating Token Index: 228

Text #3

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.9294. Min Act: -0.1700

Data Index: 2410895 (Open Web Text)

Max Activating Token Index: 262

Text #4

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.9389. Min Act: -0.1700

Data Index: 5232740 (Open Web Text)

Max Activating Token Index: 361

Text #5

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.9524. Min Act: -0.1700

Data Index: 3973683 (Open Web Text)

Max Activating Token Index: 463

Text #6

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.9491. Min Act: -0.1700

Data Index: 8793901 (Open Web Text)

Max Activating Token Index: 676

Text #7

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.9273. Min Act: -0.1700

Data Index: 5988853 (Open Web Text)

Max Activating Token Index: 215

Text #8

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.8911. Min Act: -0.1700

Data Index: 6925760 (Open Web Text)

Max Activating Token Index: 122

Text #9

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.8991. Min Act: -0.1700

Data Index: 8724515 (Open Web Text)

Max Activating Token Index: 399

Text #10

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.8890. Min Act: -0.1700

Data Index: 976986 (Open Web Text)

Max Activating Token Index: 645

Text #11

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.8814. Min Act: -0.1700

Data Index: 4728902 (Open Web Text)

Max Activating Token Index: 786

Text #12

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.8820. Min Act: -0.1700

Data Index: 8634362 (Open Web Text)

Max Activating Token Index: 77

Text #13

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.8876. Min Act: -0.1700

Data Index: 3703748 (Open Web Text)

Max Activating Token Index: 192

Text #14

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.8913. Min Act: -0.1700

Data Index: 8058955 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.8880. Min Act: -0.1700

Data Index: 7702173 (Open Web Text)

Max Activating Token Index: 123

Text #16

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.8359. Min Act: -0.1700

Data Index: 3799883 (Open Web Text)

Max Activating Token Index: 132

Text #17

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.8753. Min Act: -0.1700

Data Index: 3805098 (Open Web Text)

Max Activating Token Index: 476

Text #18

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.8375. Min Act: -0.1700

Data Index: 4586256 (Open Web Text)

Max Activating Token Index: 402

Text #19

Max Range: 3.9987. Min Range: -3.9987

Max Act: 3.8648. Min Act: -0.1700

Data Index: 2327654 (Open Web Text)

Max Activating Token Index: 52