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

Dataset: Open Web Text

Neuron 812 in Layer 1

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: 3.7985. Min Range: -3.7985

Max Act: 3.7985. Min Act: -0.1700

Data Index: 3996088 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.7683. Min Act: -0.1700

Data Index: 4893373 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.7366. Min Act: -0.1700

Data Index: 1922873 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.7136. Min Act: -0.1700

Data Index: 6423610 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6826. Min Act: -0.1700

Data Index: 2505157 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6928. Min Act: -0.1700

Data Index: 2092499 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6673. Min Act: -0.1700

Data Index: 6070333 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6669. Min Act: -0.1700

Data Index: 3655833 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6731. Min Act: -0.1700

Data Index: 6108594 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6390. Min Act: -0.1700

Data Index: 414822 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6340. Min Act: -0.1700

Data Index: 8065427 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6606. Min Act: -0.1700

Data Index: 3123055 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6302. Min Act: -0.1700

Data Index: 1915649 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6513. Min Act: -0.1700

Data Index: 3006985 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6515. Min Act: -0.1700

Data Index: 6360078 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6547. Min Act: -0.1700

Data Index: 2244228 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6628. Min Act: -0.1700

Data Index: 713120 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6312. Min Act: -0.1700

Data Index: 4636883 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6538. Min Act: -0.1700

Data Index: 3209862 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6083. Min Act: -0.1700

Data Index: 818633 (Open Web Text)

Max Activating Token Index: 3