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

Dataset: Open Web Text

Neuron 1096 in Layer 3

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: 1.8837. Min Range: -1.8837

Max Act: 1.8837. Min Act: -0.1700

Data Index: 7885011 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7657. Min Act: -0.1700

Data Index: 6095845 (Open Web Text)

Max Activating Token Index: 505

Text #2

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7625. Min Act: -0.1700

Data Index: 4950894 (Open Web Text)

Max Activating Token Index: 661

Text #3

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.8003. Min Act: -0.1700

Data Index: 8105810 (Open Web Text)

Max Activating Token Index: 416

Text #4

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7942. Min Act: -0.1700

Data Index: 6228645 (Open Web Text)

Max Activating Token Index: 108

Text #5

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7976. Min Act: -0.1700

Data Index: 278475 (Open Web Text)

Max Activating Token Index: 477

Text #6

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7922. Min Act: -0.1700

Data Index: 5621890 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.8405. Min Act: -0.1700

Data Index: 2141122 (Open Web Text)

Max Activating Token Index: 687

Text #8

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7679. Min Act: -0.1700

Data Index: 3055835 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7621. Min Act: -0.1700

Data Index: 413133 (Open Web Text)

Max Activating Token Index: 438

Text #10

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7677. Min Act: -0.1700

Data Index: 8036492 (Open Web Text)

Max Activating Token Index: 48

Text #11

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7427. Min Act: -0.1700

Data Index: 4440274 (Open Web Text)

Max Activating Token Index: 432

Text #12

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7791. Min Act: -0.1700

Data Index: 7095677 (Open Web Text)

Max Activating Token Index: 18

Text #13

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7451. Min Act: -0.1700

Data Index: 2609644 (Open Web Text)

Max Activating Token Index: 360

Text #14

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7989. Min Act: -0.1700

Data Index: 7217944 (Open Web Text)

Max Activating Token Index: 336

Text #15

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7550. Min Act: -0.1700

Data Index: 1453896 (Open Web Text)

Max Activating Token Index: 253

Text #16

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7222. Min Act: -0.1700

Data Index: 1673087 (Open Web Text)

Max Activating Token Index: 388

Text #17

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.7123. Min Act: -0.1700

Data Index: 1161539 (Open Web Text)

Max Activating Token Index: 28

Text #18

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.6906. Min Act: -0.1700

Data Index: 2620387 (Open Web Text)

Max Activating Token Index: 425

Text #19

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.6736. Min Act: -0.1700

Data Index: 4341932 (Open Web Text)

Max Activating Token Index: 410