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

Dataset: Open Web Text

Neuron 1744 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: 2.3848. Min Range: -2.3848

Max Act: 2.3848. Min Act: -0.1700

Data Index: 3955857 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.2931. Min Act: -0.1700

Data Index: 5066165 (Open Web Text)

Max Activating Token Index: 343

Text #2

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.2556. Min Act: -0.1700

Data Index: 8575811 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.2416. Min Act: -0.1700

Data Index: 1749736 (Open Web Text)

Max Activating Token Index: 229

Text #4

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.2333. Min Act: -0.1700

Data Index: 5883858 (Open Web Text)

Max Activating Token Index: 853

Text #5

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.2111. Min Act: -0.1700

Data Index: 2626563 (Open Web Text)

Max Activating Token Index: 77

Text #6

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.2249. Min Act: -0.1700

Data Index: 79959 (Open Web Text)

Max Activating Token Index: 113

Text #7

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.2090. Min Act: -0.1700

Data Index: 4260405 (Open Web Text)

Max Activating Token Index: 64

Text #8

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.2157. Min Act: -0.1697

Data Index: 387569 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.1927. Min Act: -0.1700

Data Index: 1914900 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.1848. Min Act: -0.1700

Data Index: 3444155 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.1792. Min Act: -0.1700

Data Index: 7584288 (Open Web Text)

Max Activating Token Index: 46

Text #12

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.1788. Min Act: -0.1700

Data Index: 1861216 (Open Web Text)

Max Activating Token Index: 354

Text #13

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.1834. Min Act: -0.1700

Data Index: 791971 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.1804. Min Act: -0.1700

Data Index: 4651913 (Open Web Text)

Max Activating Token Index: 340

Text #15

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.1697. Min Act: -0.1700

Data Index: 361783 (Open Web Text)

Max Activating Token Index: 46

Text #16

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.1671. Min Act: -0.1700

Data Index: 7345649 (Open Web Text)

Max Activating Token Index: 327

Text #17

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.1726. Min Act: -0.1700

Data Index: 6430381 (Open Web Text)

Max Activating Token Index: 139

Text #18

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.1728. Min Act: -0.1700

Data Index: 527750 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 2.3848. Min Range: -2.3848

Max Act: 2.1595. Min Act: -0.1700

Data Index: 4735876 (Open Web Text)

Max Activating Token Index: 6