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

Dataset: Open Web Text

Neuron 2687 in Layer 5

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: 4.8316. Min Range: -4.8316

Max Act: 4.8316. Min Act: -0.1700

Data Index: 1402833 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.7700. Min Act: -0.1700

Data Index: 7164563 (Open Web Text)

Max Activating Token Index: 188

Text #2

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.7946. Min Act: -0.1700

Data Index: 1402830 (Open Web Text)

Max Activating Token Index: 137

Text #3

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.7786. Min Act: -0.1700

Data Index: 5927819 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.7403. Min Act: -0.1700

Data Index: 3425964 (Open Web Text)

Max Activating Token Index: 131

Text #5

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.7666. Min Act: -0.1700

Data Index: 6853531 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.7339. Min Act: -0.1700

Data Index: 6853518 (Open Web Text)

Max Activating Token Index: 143

Text #7

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.7253. Min Act: -0.1700

Data Index: 3425971 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.7525. Min Act: -0.1700

Data Index: 5927814 (Open Web Text)

Max Activating Token Index: 24

Text #9

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.6943. Min Act: -0.1700

Data Index: 3425974 (Open Web Text)

Max Activating Token Index: 86

Text #10

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.7009. Min Act: -0.1700

Data Index: 7164566 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.7019. Min Act: -0.1700

Data Index: 6883836 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.7124. Min Act: -0.1700

Data Index: 7601873 (Open Web Text)

Max Activating Token Index: 196

Text #13

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.6834. Min Act: -0.1700

Data Index: 7164576 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.6882. Min Act: -0.1700

Data Index: 2923028 (Open Web Text)

Max Activating Token Index: 1009

Text #15

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.6732. Min Act: -0.1700

Data Index: 6883823 (Open Web Text)

Max Activating Token Index: 74

Text #16

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.6507. Min Act: -0.1700

Data Index: 7164577 (Open Web Text)

Max Activating Token Index: 167

Text #17

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.6362. Min Act: -0.1700

Data Index: 2525145 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.6472. Min Act: -0.1700

Data Index: 1402831 (Open Web Text)

Max Activating Token Index: 37

Text #19

Max Range: 4.8316. Min Range: -4.8316

Max Act: 4.6369. Min Act: -0.1700

Data Index: 5927815 (Open Web Text)

Max Activating Token Index: 84