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

Dataset: Open Web Text

Neuron 1748 in Layer 4

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: 3.7708. Min Range: -3.7708

Max Act: 3.7572. Min Act: -0.1700

Data Index: 5373482 (Open Web Text)

Max Activating Token Index: 324

Text #1

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.7708. Min Act: -0.1700

Data Index: 7312052 (Open Web Text)

Max Activating Token Index: 595

Text #2

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.7168. Min Act: -0.1700

Data Index: 8820024 (Open Web Text)

Max Activating Token Index: 137

Text #3

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.7014. Min Act: -0.1700

Data Index: 5170885 (Open Web Text)

Max Activating Token Index: 302

Text #4

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.6916. Min Act: -0.1700

Data Index: 2216434 (Open Web Text)

Max Activating Token Index: 585

Text #5

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.6653. Min Act: -0.1700

Data Index: 3619986 (Open Web Text)

Max Activating Token Index: 86

Text #6

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.6224. Min Act: -0.1700

Data Index: 914022 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.6062. Min Act: -0.1700

Data Index: 7727139 (Open Web Text)

Max Activating Token Index: 117

Text #8

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5822. Min Act: -0.1700

Data Index: 5576398 (Open Web Text)

Max Activating Token Index: 255

Text #9

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.6046. Min Act: -0.1700

Data Index: 61422 (Open Web Text)

Max Activating Token Index: 797

Text #10

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5885. Min Act: -0.1700

Data Index: 6662283 (Open Web Text)

Max Activating Token Index: 30

Text #11

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5462. Min Act: -0.1700

Data Index: 4227611 (Open Web Text)

Max Activating Token Index: 363

Text #12

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.6023. Min Act: -0.1700

Data Index: 1769163 (Open Web Text)

Max Activating Token Index: 402

Text #13

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5641. Min Act: -0.1700

Data Index: 8819301 (Open Web Text)

Max Activating Token Index: 704

Text #14

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5175. Min Act: -0.1700

Data Index: 6143388 (Open Web Text)

Max Activating Token Index: 55

Text #15

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5649. Min Act: -0.1700

Data Index: 1652073 (Open Web Text)

Max Activating Token Index: 71

Text #16

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5630. Min Act: -0.1700

Data Index: 4022736 (Open Web Text)

Max Activating Token Index: 963

Text #17

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5502. Min Act: -0.1700

Data Index: 7202331 (Open Web Text)

Max Activating Token Index: 27

Text #18

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5202. Min Act: -0.1700

Data Index: 5833582 (Open Web Text)

Max Activating Token Index: 954

Text #19

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.5565. Min Act: -0.1700

Data Index: 5151394 (Open Web Text)

Max Activating Token Index: 30