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

Dataset: Open Web Text

Neuron 389 in Layer 6

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: 3.6739. Min Range: -3.6739

Max Act: 3.6739. Min Act: -0.1700

Data Index: 1683513 (Open Web Text)

Max Activating Token Index: 98

Text #1

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.6254. Min Act: -0.1700

Data Index: 2002651 (Open Web Text)

Max Activating Token Index: 32

Text #2

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.6186. Min Act: -0.1700

Data Index: 6701320 (Open Web Text)

Max Activating Token Index: 260

Text #3

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.6159. Min Act: -0.1700

Data Index: 3196237 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.6195. Min Act: -0.1700

Data Index: 4747177 (Open Web Text)

Max Activating Token Index: 945

Text #5

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.5971. Min Act: -0.1700

Data Index: 6159022 (Open Web Text)

Max Activating Token Index: 314

Text #6

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.5500. Min Act: -0.1700

Data Index: 5527176 (Open Web Text)

Max Activating Token Index: 842

Text #7

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.5581. Min Act: -0.1700

Data Index: 4993590 (Open Web Text)

Max Activating Token Index: 422

Text #8

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.5468. Min Act: -0.1700

Data Index: 1003785 (Open Web Text)

Max Activating Token Index: 161

Text #9

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.5229. Min Act: -0.1700

Data Index: 6496926 (Open Web Text)

Max Activating Token Index: 296

Text #10

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.5294. Min Act: -0.1700

Data Index: 8037982 (Open Web Text)

Max Activating Token Index: 867

Text #11

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.5092. Min Act: -0.1700

Data Index: 4034163 (Open Web Text)

Max Activating Token Index: 845

Text #12

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.5110. Min Act: -0.1700

Data Index: 6240754 (Open Web Text)

Max Activating Token Index: 294

Text #13

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.4948. Min Act: -0.1700

Data Index: 6398072 (Open Web Text)

Max Activating Token Index: 121

Text #14

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.4939. Min Act: -0.1700

Data Index: 1528081 (Open Web Text)

Max Activating Token Index: 28

Text #15

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.4785. Min Act: -0.1700

Data Index: 8308578 (Open Web Text)

Max Activating Token Index: 510

Text #16

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.4996. Min Act: -0.1700

Data Index: 1539870 (Open Web Text)

Max Activating Token Index: 491

Text #17

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.5039. Min Act: -0.1700

Data Index: 8295479 (Open Web Text)

Max Activating Token Index: 72

Text #18

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.4507. Min Act: -0.1700

Data Index: 3698717 (Open Web Text)

Max Activating Token Index: 404

Text #19

Max Range: 3.6739. Min Range: -3.6739

Max Act: 3.4847. Min Act: -0.1700

Data Index: 1128254 (Open Web Text)

Max Activating Token Index: 394