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

Dataset: Open Web Text

Neuron 588 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: 0.8994. Min Range: -0.8994

Max Act: 0.8994. Min Act: -0.1700

Data Index: 5756684 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8922. Min Act: -0.1700

Data Index: 3539411 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8910. Min Act: -0.1700

Data Index: 2332015 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8854. Min Act: -0.1700

Data Index: 8402768 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8942. Min Act: -0.1700

Data Index: 169724 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8854. Min Act: -0.1700

Data Index: 483030 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8829. Min Act: -0.1700

Data Index: 7165923 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8810. Min Act: -0.1700

Data Index: 8818178 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8739. Min Act: -0.1700

Data Index: 4859813 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8704. Min Act: -0.1700

Data Index: 1301816 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8728. Min Act: -0.1700

Data Index: 2216490 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8764. Min Act: -0.1700

Data Index: 7322216 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8648. Min Act: -0.1700

Data Index: 4842055 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8732. Min Act: -0.1700

Data Index: 1763734 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8672. Min Act: -0.1700

Data Index: 5798132 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8678. Min Act: -0.1700

Data Index: 703175 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8765. Min Act: -0.1700

Data Index: 4775980 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8679. Min Act: -0.1700

Data Index: 8548724 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8686. Min Act: -0.1700

Data Index: 3978417 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8699. Min Act: -0.1700

Data Index: 5340326 (Open Web Text)

Max Activating Token Index: 1023