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

Dataset: Open Web Text

Neuron 3057 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: 3.7913. Min Range: -3.7913

Max Act: 3.7913. Min Act: -0.1700

Data Index: 368616 (Open Web Text)

Max Activating Token Index: 404

Text #1

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.6018. Min Act: -0.1700

Data Index: 576368 (Open Web Text)

Max Activating Token Index: 421

Text #2

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.6003. Min Act: -0.1700

Data Index: 3128971 (Open Web Text)

Max Activating Token Index: 807

Text #3

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.5766. Min Act: -0.1700

Data Index: 7292512 (Open Web Text)

Max Activating Token Index: 605

Text #4

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.5692. Min Act: -0.1700

Data Index: 3712405 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.5522. Min Act: -0.1700

Data Index: 724641 (Open Web Text)

Max Activating Token Index: 773

Text #6

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.5427. Min Act: -0.1700

Data Index: 6302527 (Open Web Text)

Max Activating Token Index: 143

Text #7

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.5198. Min Act: -0.1700

Data Index: 6042623 (Open Web Text)

Max Activating Token Index: 603

Text #8

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.5074. Min Act: -0.1700

Data Index: 7875555 (Open Web Text)

Max Activating Token Index: 115

Text #9

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.5202. Min Act: -0.1700

Data Index: 8757438 (Open Web Text)

Max Activating Token Index: 423

Text #10

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.4833. Min Act: -0.1700

Data Index: 5902990 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.4959. Min Act: -0.1700

Data Index: 4272655 (Open Web Text)

Max Activating Token Index: 466

Text #12

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.4880. Min Act: -0.1700

Data Index: 3776297 (Open Web Text)

Max Activating Token Index: 593

Text #13

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.4761. Min Act: -0.1700

Data Index: 8620163 (Open Web Text)

Max Activating Token Index: 148

Text #14

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.4756. Min Act: -0.1700

Data Index: 5451801 (Open Web Text)

Max Activating Token Index: 1019

Text #15

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.4712. Min Act: -0.1700

Data Index: 2954048 (Open Web Text)

Max Activating Token Index: 915

Text #16

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.4566. Min Act: -0.1700

Data Index: 4504164 (Open Web Text)

Max Activating Token Index: 975

Text #17

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.4573. Min Act: -0.1700

Data Index: 6777910 (Open Web Text)

Max Activating Token Index: 387

Text #18

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.4671. Min Act: -0.1700

Data Index: 5014176 (Open Web Text)

Max Activating Token Index: 690

Text #19

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.4566. Min Act: -0.1700

Data Index: 8688628 (Open Web Text)

Max Activating Token Index: 38