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

Dataset: Open Web Text

Neuron 857 in Layer 2

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: 4.3655. Min Range: -4.3655

Max Act: 4.3655. Min Act: -0.1700

Data Index: 2409177 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.3033. Min Act: -0.1700

Data Index: 6046473 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.2842. Min Act: -0.1700

Data Index: 2409182 (Open Web Text)

Max Activating Token Index: 82

Text #3

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.2650. Min Act: -0.1700

Data Index: 344426 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.2543. Min Act: -0.1700

Data Index: 8693609 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.2332. Min Act: -0.1700

Data Index: 4100114 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.2577. Min Act: -0.1700

Data Index: 2409167 (Open Web Text)

Max Activating Token Index: 109

Text #7

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.1549. Min Act: -0.1700

Data Index: 8370325 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.1892. Min Act: -0.1700

Data Index: 8727860 (Open Web Text)

Max Activating Token Index: 77

Text #9

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.1703. Min Act: -0.1700

Data Index: 5300326 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.1775. Min Act: -0.1700

Data Index: 5861240 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.1660. Min Act: -0.1700

Data Index: 3642863 (Open Web Text)

Max Activating Token Index: 20

Text #12

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.1854. Min Act: -0.1700

Data Index: 7982646 (Open Web Text)

Max Activating Token Index: 21

Text #13

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.1474. Min Act: -0.1700

Data Index: 344421 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.1339. Min Act: -0.1700

Data Index: 344419 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.1294. Min Act: -0.1700

Data Index: 8081443 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.1291. Min Act: -0.1700

Data Index: 2409164 (Open Web Text)

Max Activating Token Index: 194

Text #17

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.1086. Min Act: -0.1700

Data Index: 348638 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.1159. Min Act: -0.1700

Data Index: 4100116 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.3655. Min Range: -4.3655

Max Act: 4.1211. Min Act: -0.1700

Data Index: 2453450 (Open Web Text)

Max Activating Token Index: 5