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

Dataset: Open Web Text

Neuron 2446 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: 3.1425. Min Range: -3.1425

Max Act: 3.1425. Min Act: -0.1700

Data Index: 1996430 (Open Web Text)

Max Activating Token Index: 836

Text #1

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.1005. Min Act: -0.1700

Data Index: 2156837 (Open Web Text)

Max Activating Token Index: 50

Text #2

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 2535595 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 2850332 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 3543537 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0786. Min Act: -0.1700

Data Index: 8546954 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 4752080 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 1712922 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 1129532 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 2409356 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 3509701 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 7167773 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 4154099 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 408444 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 7661696 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 3256480 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 6431018 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 1647885 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 4108735 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.1425. Min Range: -3.1425

Max Act: 3.0892. Min Act: -0.1700

Data Index: 3178293 (Open Web Text)

Max Activating Token Index: 2