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

Dataset: Open Web Text

Neuron 1720 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: 3.3703. Min Range: -3.3703

Max Act: 3.3703. Min Act: -0.1700

Data Index: 4517502 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2663. Min Act: -0.1700

Data Index: 5936757 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2638. Min Act: -0.1700

Data Index: 531640 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2606. Min Act: -0.1700

Data Index: 3745992 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2770. Min Act: -0.1700

Data Index: 7781382 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2415. Min Act: -0.1700

Data Index: 3954014 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2466. Min Act: -0.1700

Data Index: 1016731 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2608. Min Act: -0.1700

Data Index: 8646242 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2397. Min Act: -0.1700

Data Index: 6619507 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2301. Min Act: -0.1700

Data Index: 2901292 (Open Web Text)

Max Activating Token Index: 255

Text #10

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2222. Min Act: -0.1700

Data Index: 868701 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2172. Min Act: -0.1700

Data Index: 5782723 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2098. Min Act: -0.1700

Data Index: 2858522 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2044. Min Act: -0.1700

Data Index: 1635207 (Open Web Text)

Max Activating Token Index: 989

Text #14

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1958. Min Act: -0.1700

Data Index: 564185 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1980. Min Act: -0.1700

Data Index: 4993565 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1871. Min Act: -0.1700

Data Index: 5434643 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1848. Min Act: -0.1700

Data Index: 853878 (Open Web Text)

Max Activating Token Index: 416

Text #18

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1769. Min Act: -0.1700

Data Index: 7232078 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1821. Min Act: -0.1700

Data Index: 7026791 (Open Web Text)

Max Activating Token Index: 6