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

Dataset: Open Web Text

Neuron 1022 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: 3.7985. Min Range: -3.7985

Max Act: 3.7985. Min Act: -0.1700

Data Index: 940208 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.7628. Min Act: -0.1700

Data Index: 5736221 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.7656. Min Act: -0.1700

Data Index: 5663195 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.7421. Min Act: -0.1700

Data Index: 4023898 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.7134. Min Act: -0.1700

Data Index: 6016178 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.7062. Min Act: -0.1700

Data Index: 1788122 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.7163. Min Act: -0.1700

Data Index: 730073 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.7060. Min Act: -0.1700

Data Index: 4577634 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6830. Min Act: -0.1700

Data Index: 1287137 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6830. Min Act: -0.1700

Data Index: 5500443 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6861. Min Act: -0.1700

Data Index: 5402799 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6830. Min Act: -0.1700

Data Index: 849197 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6760. Min Act: -0.1700

Data Index: 4914739 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6791. Min Act: -0.1700

Data Index: 1112666 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6836. Min Act: -0.1700

Data Index: 3508383 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6979. Min Act: -0.1700

Data Index: 4036939 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6691. Min Act: -0.1700

Data Index: 3183529 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6839. Min Act: -0.1700

Data Index: 2217027 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6765. Min Act: -0.1700

Data Index: 2846592 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.7985. Min Range: -3.7985

Max Act: 3.6830. Min Act: -0.1700

Data Index: 668519 (Open Web Text)

Max Activating Token Index: 2