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

Dataset: Open Web Text

Neuron 847 in Layer 3

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: 3.5464. Min Range: -3.5464

Max Act: 3.5464. Min Act: -0.1700

Data Index: 7303771 (Open Web Text)

Max Activating Token Index: 473

Text #1

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.5338. Min Act: -0.1700

Data Index: 4758109 (Open Web Text)

Max Activating Token Index: 453

Text #2

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.4705. Min Act: -0.1700

Data Index: 8610892 (Open Web Text)

Max Activating Token Index: 976

Text #3

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.4210. Min Act: -0.1700

Data Index: 5058380 (Open Web Text)

Max Activating Token Index: 999

Text #4

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.4251. Min Act: -0.1700

Data Index: 881888 (Open Web Text)

Max Activating Token Index: 132

Text #5

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.4548. Min Act: -0.1700

Data Index: 1322040 (Open Web Text)

Max Activating Token Index: 423

Text #6

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.4224. Min Act: -0.1700

Data Index: 7033676 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.4227. Min Act: -0.1700

Data Index: 8452527 (Open Web Text)

Max Activating Token Index: 513

Text #8

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.4059. Min Act: -0.1700

Data Index: 6941875 (Open Web Text)

Max Activating Token Index: 43

Text #9

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.4248. Min Act: -0.1700

Data Index: 1813095 (Open Web Text)

Max Activating Token Index: 589

Text #10

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.3852. Min Act: -0.1700

Data Index: 3801142 (Open Web Text)

Max Activating Token Index: 674

Text #11

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.3870. Min Act: -0.1700

Data Index: 8580257 (Open Web Text)

Max Activating Token Index: 179

Text #12

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.3880. Min Act: -0.1700

Data Index: 2626893 (Open Web Text)

Max Activating Token Index: 29

Text #13

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.3880. Min Act: -0.1700

Data Index: 634322 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.3764. Min Act: -0.1700

Data Index: 7062822 (Open Web Text)

Max Activating Token Index: 587

Text #15

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.4060. Min Act: -0.1700

Data Index: 424995 (Open Web Text)

Max Activating Token Index: 83

Text #16

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.4096. Min Act: -0.1700

Data Index: 3228828 (Open Web Text)

Max Activating Token Index: 370

Text #17

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.3771. Min Act: -0.1700

Data Index: 506066 (Open Web Text)

Max Activating Token Index: 49

Text #18

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.3742. Min Act: -0.1700

Data Index: 1788010 (Open Web Text)

Max Activating Token Index: 84

Text #19

Max Range: 3.5464. Min Range: -3.5464

Max Act: 3.3641. Min Act: -0.1700

Data Index: 1271119 (Open Web Text)

Max Activating Token Index: 20