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

Dataset: Open Web Text

Neuron 1989 in Layer 0

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: 3.4788. Min Range: -3.4788

Max Act: 3.4644. Min Act: -0.1700

Data Index: 6426527 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.4788. Min Act: -0.1700

Data Index: 6359280 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.4419. Min Act: -0.1700

Data Index: 6000899 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.4011. Min Act: -0.1700

Data Index: 677459 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.4073. Min Act: -0.1700

Data Index: 3324273 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3744. Min Act: -0.1700

Data Index: 7118357 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3600. Min Act: -0.1700

Data Index: 2483617 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3655. Min Act: -0.1700

Data Index: 2445893 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3801. Min Act: -0.1700

Data Index: 2316569 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3807. Min Act: -0.1700

Data Index: 4122883 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3665. Min Act: -0.1700

Data Index: 1425628 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3878. Min Act: -0.1700

Data Index: 8775739 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3838. Min Act: -0.1700

Data Index: 3246456 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3701. Min Act: -0.1700

Data Index: 8347248 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3907. Min Act: -0.1700

Data Index: 8209891 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3705. Min Act: -0.1700

Data Index: 6942352 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3345. Min Act: -0.1700

Data Index: 1411613 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3525. Min Act: -0.1700

Data Index: 3877407 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3388. Min Act: -0.1700

Data Index: 3696883 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.3414. Min Act: -0.1700

Data Index: 24451 (Open Web Text)

Max Activating Token Index: 5