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

Dataset: Open Web Text

Neuron 841 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: 6.4192. Min Range: -6.4192

Max Act: 6.4192. Min Act: -0.1700

Data Index: 158295 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.3444. Min Act: -0.1699

Data Index: 1244545 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.3218. Min Act: -0.1699

Data Index: 5696656 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.3089. Min Act: -0.1697

Data Index: 935012 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.3263. Min Act: -0.1700

Data Index: 989992 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.3021. Min Act: -0.1700

Data Index: 56994 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.2988. Min Act: -0.1700

Data Index: 6168969 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.2809. Min Act: -0.1699

Data Index: 7659365 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.3007. Min Act: -0.1699

Data Index: 3016890 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.2568. Min Act: -0.1700

Data Index: 5215854 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.2347. Min Act: -0.1700

Data Index: 1138365 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.2555. Min Act: -0.1700

Data Index: 1771252 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.2561. Min Act: -0.1700

Data Index: 133188 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.2756. Min Act: -0.1700

Data Index: 4272716 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.2708. Min Act: -0.1700

Data Index: 6844101 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.2468. Min Act: -0.1700

Data Index: 8371 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.2413. Min Act: -0.1700

Data Index: 5596856 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.2062. Min Act: -0.1699

Data Index: 3213670 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.2110. Min Act: -0.1700

Data Index: 3309945 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 6.4192. Min Range: -6.4192

Max Act: 6.2203. Min Act: -0.1700

Data Index: 56863 (Open Web Text)

Max Activating Token Index: 5