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

Dataset: Open Web Text

Neuron 1791 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: 4.3723. Min Range: -4.3723

Max Act: 4.3723. Min Act: -0.1700

Data Index: 2718320 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.2902. Min Act: -0.1700

Data Index: 1962966 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.2748. Min Act: -0.1700

Data Index: 6202323 (Open Web Text)

Max Activating Token Index: 67

Text #3

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.2567. Min Act: -0.1700

Data Index: 7811553 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.2181. Min Act: -0.1700

Data Index: 5431157 (Open Web Text)

Max Activating Token Index: 99

Text #5

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.2182. Min Act: -0.1700

Data Index: 6227370 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.2202. Min Act: -0.1700

Data Index: 5882387 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.2097. Min Act: -0.1700

Data Index: 5730534 (Open Web Text)

Max Activating Token Index: 26

Text #8

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.2307. Min Act: -0.1700

Data Index: 1361387 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.2394. Min Act: -0.1700

Data Index: 8004501 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.2069. Min Act: -0.1700

Data Index: 5103783 (Open Web Text)

Max Activating Token Index: 421

Text #11

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.2066. Min Act: -0.1700

Data Index: 4086933 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.2058. Min Act: -0.1700

Data Index: 4975570 (Open Web Text)

Max Activating Token Index: 963

Text #13

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.1749. Min Act: -0.1700

Data Index: 1418159 (Open Web Text)

Max Activating Token Index: 643

Text #14

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.1881. Min Act: -0.1700

Data Index: 6555963 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.1789. Min Act: -0.1700

Data Index: 2069089 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.1749. Min Act: -0.1700

Data Index: 5853479 (Open Web Text)

Max Activating Token Index: 403

Text #17

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.1551. Min Act: -0.1700

Data Index: 5919783 (Open Web Text)

Max Activating Token Index: 135

Text #18

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.1709. Min Act: -0.1700

Data Index: 5980677 (Open Web Text)

Max Activating Token Index: 683

Text #19

Max Range: 4.3723. Min Range: -4.3723

Max Act: 4.1590. Min Act: -0.1700

Data Index: 2384301 (Open Web Text)

Max Activating Token Index: 5