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

Dataset: Open Web Text

Neuron 364 in Layer 4

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: 5.5887. Min Range: -5.5887

Max Act: 5.5887. Min Act: -0.1700

Data Index: 7219090 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.2486. Min Act: -0.1700

Data Index: 6643087 (Open Web Text)

Max Activating Token Index: 672

Text #2

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.2429. Min Act: -0.1700

Data Index: 3060274 (Open Web Text)

Max Activating Token Index: 596

Text #3

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.2447. Min Act: -0.1700

Data Index: 6102396 (Open Web Text)

Max Activating Token Index: 386

Text #4

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.1778. Min Act: -0.1700

Data Index: 7777222 (Open Web Text)

Max Activating Token Index: 936

Text #5

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.1212. Min Act: -0.1700

Data Index: 2797979 (Open Web Text)

Max Activating Token Index: 426

Text #6

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.1214. Min Act: -0.1700

Data Index: 2908681 (Open Web Text)

Max Activating Token Index: 806

Text #7

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.1483. Min Act: -0.1700

Data Index: 4664463 (Open Web Text)

Max Activating Token Index: 108

Text #8

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.1382. Min Act: -0.1700

Data Index: 6575454 (Open Web Text)

Max Activating Token Index: 503

Text #9

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.1309. Min Act: -0.1700

Data Index: 2633842 (Open Web Text)

Max Activating Token Index: 322

Text #10

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.0833. Min Act: -0.1700

Data Index: 360787 (Open Web Text)

Max Activating Token Index: 331

Text #11

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.1194. Min Act: -0.1700

Data Index: 338370 (Open Web Text)

Max Activating Token Index: 560

Text #12

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.0980. Min Act: -0.1700

Data Index: 4934423 (Open Web Text)

Max Activating Token Index: 646

Text #13

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.1285. Min Act: -0.1700

Data Index: 7704893 (Open Web Text)

Max Activating Token Index: 805

Text #14

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.0681. Min Act: -0.1700

Data Index: 3535241 (Open Web Text)

Max Activating Token Index: 740

Text #15

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.0685. Min Act: -0.1700

Data Index: 5812525 (Open Web Text)

Max Activating Token Index: 92

Text #16

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.0896. Min Act: -0.1700

Data Index: 7479025 (Open Web Text)

Max Activating Token Index: 660

Text #17

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.1311. Min Act: -0.1700

Data Index: 1039387 (Open Web Text)

Max Activating Token Index: 950

Text #18

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.0930. Min Act: -0.1700

Data Index: 2529433 (Open Web Text)

Max Activating Token Index: 752

Text #19

Max Range: 5.5887. Min Range: -5.5887

Max Act: 5.0744. Min Act: -0.1700

Data Index: 2275792 (Open Web Text)

Max Activating Token Index: 375