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

Dataset: Open Web Text

Neuron 2776 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: 5.0397. Min Range: -5.0397

Max Act: 5.0362. Min Act: -0.1700

Data Index: 7873499 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 5.0397. Min Range: -5.0397

Max Act: 5.0397. Min Act: -0.1700

Data Index: 1892079 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.0397. Min Range: -5.0397

Max Act: 5.0214. Min Act: -0.1700

Data Index: 1491500 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 5.0397. Min Range: -5.0397

Max Act: 5.0016. Min Act: -0.1700

Data Index: 8218969 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 5.0397. Min Range: -5.0397

Max Act: 5.0111. Min Act: -0.1700

Data Index: 411322 (Open Web Text)

Max Activating Token Index: 20

Text #5

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9854. Min Act: -0.1700

Data Index: 1557504 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9755. Min Act: -0.1700

Data Index: 8002536 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9876. Min Act: -0.1700

Data Index: 3855268 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9817. Min Act: -0.1700

Data Index: 7497378 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9972. Min Act: -0.1700

Data Index: 989373 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9709. Min Act: -0.1700

Data Index: 8449134 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9523. Min Act: -0.1700

Data Index: 4797081 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9603. Min Act: -0.1700

Data Index: 2610622 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9562. Min Act: -0.1700

Data Index: 4747357 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9511. Min Act: -0.1700

Data Index: 516036 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9635. Min Act: -0.1700

Data Index: 8147090 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9478. Min Act: -0.1700

Data Index: 3029601 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9307. Min Act: -0.1700

Data Index: 19084 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9134. Min Act: -0.1700

Data Index: 4422108 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 5.0397. Min Range: -5.0397

Max Act: 4.9375. Min Act: -0.1700

Data Index: 6145881 (Open Web Text)

Max Activating Token Index: 6