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

Dataset: Open Web Text

Neuron 1100 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: 3.3846. Min Range: -3.3846

Max Act: 3.3846. Min Act: -0.1700

Data Index: 7468634 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.3823. Min Act: -0.1700

Data Index: 1819741 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.3244. Min Act: -0.1700

Data Index: 5944850 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.3380. Min Act: -0.1700

Data Index: 6279270 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.3378. Min Act: -0.1700

Data Index: 8662058 (Open Web Text)

Max Activating Token Index: 222

Text #5

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.3328. Min Act: -0.1700

Data Index: 5505949 (Open Web Text)

Max Activating Token Index: 129

Text #6

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.3249. Min Act: -0.1700

Data Index: 3168960 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.2915. Min Act: -0.1700

Data Index: 3648131 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.2840. Min Act: -0.1700

Data Index: 4190144 (Open Web Text)

Max Activating Token Index: 346

Text #9

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.3012. Min Act: -0.1700

Data Index: 7931771 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.2894. Min Act: -0.1700

Data Index: 1943036 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.2838. Min Act: -0.1700

Data Index: 3153233 (Open Web Text)

Max Activating Token Index: 154

Text #12

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.2892. Min Act: -0.1700

Data Index: 4404606 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.2720. Min Act: -0.1700

Data Index: 2579476 (Open Web Text)

Max Activating Token Index: 87

Text #14

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.2787. Min Act: -0.1700

Data Index: 1556686 (Open Web Text)

Max Activating Token Index: 279

Text #15

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.2806. Min Act: -0.1700

Data Index: 9650 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.2792. Min Act: -0.1700

Data Index: 7391730 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.2772. Min Act: -0.1700

Data Index: 12262 (Open Web Text)

Max Activating Token Index: 240

Text #18

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.2643. Min Act: -0.1700

Data Index: 2154577 (Open Web Text)

Max Activating Token Index: 479

Text #19

Max Range: 3.3846. Min Range: -3.3846

Max Act: 3.2662. Min Act: -0.1700

Data Index: 4964417 (Open Web Text)

Max Activating Token Index: 21