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

Dataset: Open Web Text

Neuron 3045 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: 3.5001. Min Range: -3.5001

Max Act: 3.5001. Min Act: -0.1700

Data Index: 6118504 (Open Web Text)

Max Activating Token Index: 504

Text #1

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3857. Min Act: -0.1700

Data Index: 3913421 (Open Web Text)

Max Activating Token Index: 352

Text #2

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3832. Min Act: -0.1700

Data Index: 5911787 (Open Web Text)

Max Activating Token Index: 582

Text #3

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.4011. Min Act: -0.1700

Data Index: 4548543 (Open Web Text)

Max Activating Token Index: 595

Text #4

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3409. Min Act: -0.1700

Data Index: 399565 (Open Web Text)

Max Activating Token Index: 846

Text #5

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3509. Min Act: -0.1700

Data Index: 4303766 (Open Web Text)

Max Activating Token Index: 26

Text #6

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3051. Min Act: -0.1700

Data Index: 4210002 (Open Web Text)

Max Activating Token Index: 533

Text #7

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.2394. Min Act: -0.1700

Data Index: 5939026 (Open Web Text)

Max Activating Token Index: 268

Text #8

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.2493. Min Act: -0.1700

Data Index: 5366737 (Open Web Text)

Max Activating Token Index: 211

Text #9

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.2225. Min Act: -0.1700

Data Index: 2444931 (Open Web Text)

Max Activating Token Index: 59

Text #10

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.2450. Min Act: -0.1700

Data Index: 4010300 (Open Web Text)

Max Activating Token Index: 764

Text #11

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.1992. Min Act: -0.1700

Data Index: 216484 (Open Web Text)

Max Activating Token Index: 410

Text #12

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.2096. Min Act: -0.1700

Data Index: 1453267 (Open Web Text)

Max Activating Token Index: 543

Text #13

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.2001. Min Act: -0.1700

Data Index: 2436644 (Open Web Text)

Max Activating Token Index: 949

Text #14

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.1973. Min Act: -0.1700

Data Index: 2412338 (Open Web Text)

Max Activating Token Index: 73

Text #15

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.2114. Min Act: -0.1700

Data Index: 4812514 (Open Web Text)

Max Activating Token Index: 329

Text #16

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.1926. Min Act: -0.1700

Data Index: 7184546 (Open Web Text)

Max Activating Token Index: 848

Text #17

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.1877. Min Act: -0.1700

Data Index: 4709118 (Open Web Text)

Max Activating Token Index: 116

Text #18

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.1502. Min Act: -0.1700

Data Index: 3862535 (Open Web Text)

Max Activating Token Index: 350

Text #19

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.1878. Min Act: -0.1700

Data Index: 2891166 (Open Web Text)

Max Activating Token Index: 388