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

Dataset: Open Web Text

Neuron 2845 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: 5.3213. Min Range: -5.3213

Max Act: 5.3213. Min Act: -0.1700

Data Index: 6795895 (Open Web Text)

Max Activating Token Index: 371

Text #1

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.2833. Min Act: -0.1700

Data Index: 1940169 (Open Web Text)

Max Activating Token Index: 398

Text #2

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.1561. Min Act: -0.1700

Data Index: 5347609 (Open Web Text)

Max Activating Token Index: 61

Text #3

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.1237. Min Act: -0.1700

Data Index: 2098799 (Open Web Text)

Max Activating Token Index: 266

Text #4

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.1150. Min Act: -0.1700

Data Index: 7359954 (Open Web Text)

Max Activating Token Index: 571

Text #5

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.0919. Min Act: -0.1700

Data Index: 7608682 (Open Web Text)

Max Activating Token Index: 1008

Text #6

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.1085. Min Act: -0.1700

Data Index: 4957006 (Open Web Text)

Max Activating Token Index: 703

Text #7

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.1015. Min Act: -0.1700

Data Index: 2290673 (Open Web Text)

Max Activating Token Index: 369

Text #8

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.0730. Min Act: -0.1700

Data Index: 7669368 (Open Web Text)

Max Activating Token Index: 682

Text #9

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.0614. Min Act: -0.1700

Data Index: 2899598 (Open Web Text)

Max Activating Token Index: 341

Text #10

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.1011. Min Act: -0.1700

Data Index: 6084723 (Open Web Text)

Max Activating Token Index: 531

Text #11

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.9963. Min Act: -0.1700

Data Index: 71202 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.0513. Min Act: -0.1700

Data Index: 2507486 (Open Web Text)

Max Activating Token Index: 717

Text #13

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.0276. Min Act: -0.1700

Data Index: 7616202 (Open Web Text)

Max Activating Token Index: 834

Text #14

Max Range: 5.3213. Min Range: -5.3213

Max Act: 5.0371. Min Act: -0.1700

Data Index: 5154201 (Open Web Text)

Max Activating Token Index: 902

Text #15

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.9649. Min Act: -0.1700

Data Index: 568526 (Open Web Text)

Max Activating Token Index: 346

Text #16

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.9687. Min Act: -0.1700

Data Index: 7422315 (Open Web Text)

Max Activating Token Index: 767

Text #17

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.9531. Min Act: -0.1700

Data Index: 1754522 (Open Web Text)

Max Activating Token Index: 534

Text #18

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.9597. Min Act: -0.1700

Data Index: 4405975 (Open Web Text)

Max Activating Token Index: 237

Text #19

Max Range: 5.3213. Min Range: -5.3213

Max Act: 4.9885. Min Act: -0.1700

Data Index: 5359979 (Open Web Text)

Max Activating Token Index: 174