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

Dataset: Open Web Text

Neuron 957 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: 3.2885. Min Range: -3.2885

Max Act: 3.2885. Min Act: -0.1700

Data Index: 574173 (Open Web Text)

Max Activating Token Index: 139

Text #1

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.2539. Min Act: -0.1700

Data Index: 6112697 (Open Web Text)

Max Activating Token Index: 511

Text #2

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.2182. Min Act: -0.1700

Data Index: 6504350 (Open Web Text)

Max Activating Token Index: 624

Text #3

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.2346. Min Act: -0.1700

Data Index: 2721394 (Open Web Text)

Max Activating Token Index: 600

Text #4

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1573. Min Act: -0.1700

Data Index: 5218456 (Open Web Text)

Max Activating Token Index: 136

Text #5

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1761. Min Act: -0.1700

Data Index: 5197663 (Open Web Text)

Max Activating Token Index: 278

Text #6

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1638. Min Act: -0.1700

Data Index: 7929473 (Open Web Text)

Max Activating Token Index: 634

Text #7

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1420. Min Act: -0.1700

Data Index: 4188023 (Open Web Text)

Max Activating Token Index: 731

Text #8

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1500. Min Act: -0.1700

Data Index: 5071073 (Open Web Text)

Max Activating Token Index: 956

Text #9

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1662. Min Act: -0.1700

Data Index: 6005789 (Open Web Text)

Max Activating Token Index: 764

Text #10

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1317. Min Act: -0.1700

Data Index: 4071326 (Open Web Text)

Max Activating Token Index: 255

Text #11

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1364. Min Act: -0.1700

Data Index: 3742766 (Open Web Text)

Max Activating Token Index: 848

Text #12

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.0818. Min Act: -0.1700

Data Index: 309654 (Open Web Text)

Max Activating Token Index: 644

Text #13

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.0981. Min Act: -0.1700

Data Index: 6000503 (Open Web Text)

Max Activating Token Index: 181

Text #14

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1059. Min Act: -0.1700

Data Index: 1688686 (Open Web Text)

Max Activating Token Index: 385

Text #15

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1221. Min Act: -0.1700

Data Index: 3067048 (Open Web Text)

Max Activating Token Index: 442

Text #16

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.0943. Min Act: -0.1700

Data Index: 3684992 (Open Web Text)

Max Activating Token Index: 1020

Text #17

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.0829. Min Act: -0.1700

Data Index: 1619145 (Open Web Text)

Max Activating Token Index: 67

Text #18

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.0870. Min Act: -0.1700

Data Index: 1851242 (Open Web Text)

Max Activating Token Index: 456

Text #19

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.0805. Min Act: -0.1700

Data Index: 4994161 (Open Web Text)

Max Activating Token Index: 143