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

Dataset: Open Web Text

Neuron 1476 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: 3.8003. Min Range: -3.8003

Max Act: 3.8003. Min Act: -0.1697

Data Index: 1190940 (Open Web Text)

Max Activating Token Index: 443

Text #1

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.6447. Min Act: -0.1700

Data Index: 2257951 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5210. Min Act: -0.1700

Data Index: 4170948 (Open Web Text)

Max Activating Token Index: 884

Text #3

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.4754. Min Act: -0.1700

Data Index: 1190941 (Open Web Text)

Max Activating Token Index: 850

Text #4

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.4561. Min Act: -0.1700

Data Index: 4170947 (Open Web Text)

Max Activating Token Index: 268

Text #5

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.3619. Min Act: -0.1700

Data Index: 8248882 (Open Web Text)

Max Activating Token Index: 651

Text #6

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.3337. Min Act: -0.1700

Data Index: 6099316 (Open Web Text)

Max Activating Token Index: 347

Text #7

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.3331. Min Act: -0.1700

Data Index: 6099322 (Open Web Text)

Max Activating Token Index: 380

Text #8

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.3408. Min Act: -0.1700

Data Index: 59163 (Open Web Text)

Max Activating Token Index: 439

Text #9

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.3847. Min Act: -0.1700

Data Index: 1190945 (Open Web Text)

Max Activating Token Index: 472

Text #10

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.3372. Min Act: -0.1700

Data Index: 6099306 (Open Web Text)

Max Activating Token Index: 60

Text #11

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.3307. Min Act: -0.1700

Data Index: 8013896 (Open Web Text)

Max Activating Token Index: 355

Text #12

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.3389. Min Act: -0.1700

Data Index: 2820045 (Open Web Text)

Max Activating Token Index: 129

Text #13

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.3069. Min Act: -0.1700

Data Index: 5942993 (Open Web Text)

Max Activating Token Index: 148

Text #14

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.3479. Min Act: -0.1700

Data Index: 1190944 (Open Web Text)

Max Activating Token Index: 677

Text #15

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.3284. Min Act: -0.1700

Data Index: 8248887 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.3314. Min Act: -0.1700

Data Index: 1765553 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.3140. Min Act: -0.1700

Data Index: 2844488 (Open Web Text)

Max Activating Token Index: 788

Text #18

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.3062. Min Act: -0.1700

Data Index: 185156 (Open Web Text)

Max Activating Token Index: 106

Text #19

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.2995. Min Act: -0.1700

Data Index: 2722 (Open Web Text)

Max Activating Token Index: 436