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

Dataset: Open Web Text

Neuron 278 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: 6.4975. Min Range: -6.4975

Max Act: 6.4975. Min Act: -0.1700

Data Index: 7206709 (Open Web Text)

Max Activating Token Index: 32

Text #1

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.3861. Min Act: -0.1699

Data Index: 5307552 (Open Web Text)

Max Activating Token Index: 63

Text #2

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.3446. Min Act: -0.1567

Data Index: 3889977 (Open Web Text)

Max Activating Token Index: 23

Text #3

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.2523. Min Act: -0.1584

Data Index: 2229471 (Open Web Text)

Max Activating Token Index: 112

Text #4

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.2382. Min Act: -0.1563

Data Index: 4025888 (Open Web Text)

Max Activating Token Index: 112

Text #5

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.1664. Min Act: -0.1628

Data Index: 8255861 (Open Web Text)

Max Activating Token Index: 116

Text #6

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.1853. Min Act: -0.1557

Data Index: 7782135 (Open Web Text)

Max Activating Token Index: 23

Text #7

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.1612. Min Act: -0.1698

Data Index: 3197744 (Open Web Text)

Max Activating Token Index: 205

Text #8

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.1499. Min Act: -0.1648

Data Index: 4385986 (Open Web Text)

Max Activating Token Index: 54

Text #9

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.1073. Min Act: -0.1688

Data Index: 1939510 (Open Web Text)

Max Activating Token Index: 26

Text #10

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.1350. Min Act: -0.1659

Data Index: 8603181 (Open Web Text)

Max Activating Token Index: 273

Text #11

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.0939. Min Act: -0.1700

Data Index: 3362431 (Open Web Text)

Max Activating Token Index: 36

Text #12

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.0636. Min Act: -0.1628

Data Index: 5475953 (Open Web Text)

Max Activating Token Index: 126

Text #13

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.0818. Min Act: -0.0264

Data Index: 1960637 (Open Web Text)

Max Activating Token Index: 277

Text #14

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.0242. Min Act: -0.1699

Data Index: 4385662 (Open Web Text)

Max Activating Token Index: 227

Text #15

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.0203. Min Act: -0.1696

Data Index: 1608961 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 6.4975. Min Range: -6.4975

Max Act: 6.0054. Min Act: -0.0264

Data Index: 699508 (Open Web Text)

Max Activating Token Index: 46

Text #17

Max Range: 6.4975. Min Range: -6.4975

Max Act: 5.9946. Min Act: -0.1700

Data Index: 425795 (Open Web Text)

Max Activating Token Index: 149

Text #18

Max Range: 6.4975. Min Range: -6.4975

Max Act: 5.9859. Min Act: -0.1617

Data Index: 3090892 (Open Web Text)

Max Activating Token Index: 71

Text #19

Max Range: 6.4975. Min Range: -6.4975

Max Act: 5.9704. Min Act: -0.1074

Data Index: 5020622 (Open Web Text)

Max Activating Token Index: 40