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

Dataset: Open Web Text

Neuron 766 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: 3.9879. Min Range: -3.9879

Max Act: 3.9879. Min Act: -0.1700

Data Index: 986067 (Open Web Text)

Max Activating Token Index: 390

Text #1

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7817. Min Act: -0.1700

Data Index: 115344 (Open Web Text)

Max Activating Token Index: 415

Text #2

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7666. Min Act: -0.1700

Data Index: 7419739 (Open Web Text)

Max Activating Token Index: 841

Text #3

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6955. Min Act: -0.1700

Data Index: 3776930 (Open Web Text)

Max Activating Token Index: 541

Text #4

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7625. Min Act: -0.1700

Data Index: 6326224 (Open Web Text)

Max Activating Token Index: 190

Text #5

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6988. Min Act: -0.1700

Data Index: 3540819 (Open Web Text)

Max Activating Token Index: 155

Text #6

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6949. Min Act: -0.1700

Data Index: 5840916 (Open Web Text)

Max Activating Token Index: 552

Text #7

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6694. Min Act: -0.1700

Data Index: 5819601 (Open Web Text)

Max Activating Token Index: 602

Text #8

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6980. Min Act: -0.1700

Data Index: 6444151 (Open Web Text)

Max Activating Token Index: 882

Text #9

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7289. Min Act: -0.1700

Data Index: 3728533 (Open Web Text)

Max Activating Token Index: 388

Text #10

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7252. Min Act: -0.1700

Data Index: 5417404 (Open Web Text)

Max Activating Token Index: 102

Text #11

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7183. Min Act: -0.1700

Data Index: 5691259 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7111. Min Act: -0.1700

Data Index: 3933438 (Open Web Text)

Max Activating Token Index: 327

Text #13

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7219. Min Act: -0.1700

Data Index: 2314198 (Open Web Text)

Max Activating Token Index: 898

Text #14

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.7163. Min Act: -0.1700

Data Index: 5915283 (Open Web Text)

Max Activating Token Index: 787

Text #15

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6138. Min Act: -0.1700

Data Index: 7730732 (Open Web Text)

Max Activating Token Index: 491

Text #16

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6283. Min Act: -0.1700

Data Index: 6298227 (Open Web Text)

Max Activating Token Index: 805

Text #17

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6598. Min Act: -0.1700

Data Index: 2487964 (Open Web Text)

Max Activating Token Index: 573

Text #18

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6019. Min Act: -0.1700

Data Index: 5139347 (Open Web Text)

Max Activating Token Index: 889

Text #19

Max Range: 3.9879. Min Range: -3.9879

Max Act: 3.6001. Min Act: -0.1700

Data Index: 4229392 (Open Web Text)

Max Activating Token Index: 607