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

Dataset: Open Web Text

Neuron 1163 in Layer 2

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: 5.6970. Min Range: -5.6970

Max Act: 5.6970. Min Act: -0.1700

Data Index: 4191778 (Open Web Text)

Max Activating Token Index: 995

Text #1

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.6108. Min Act: -0.1700

Data Index: 6772397 (Open Web Text)

Max Activating Token Index: 965

Text #2

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.6216. Min Act: -0.1700

Data Index: 7612400 (Open Web Text)

Max Activating Token Index: 195

Text #3

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.6247. Min Act: -0.1700

Data Index: 439859 (Open Web Text)

Max Activating Token Index: 304

Text #4

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.6333. Min Act: -0.1700

Data Index: 5215595 (Open Web Text)

Max Activating Token Index: 1007

Text #5

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.6034. Min Act: -0.1700

Data Index: 2499854 (Open Web Text)

Max Activating Token Index: 285

Text #6

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5834. Min Act: -0.1700

Data Index: 6228246 (Open Web Text)

Max Activating Token Index: 550

Text #7

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.6278. Min Act: -0.1700

Data Index: 5051088 (Open Web Text)

Max Activating Token Index: 422

Text #8

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5948. Min Act: -0.1700

Data Index: 2998675 (Open Web Text)

Max Activating Token Index: 552

Text #9

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5484. Min Act: -0.1700

Data Index: 5591929 (Open Web Text)

Max Activating Token Index: 168

Text #10

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5710. Min Act: -0.1700

Data Index: 4830610 (Open Web Text)

Max Activating Token Index: 866

Text #11

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5617. Min Act: -0.1700

Data Index: 4693866 (Open Web Text)

Max Activating Token Index: 677

Text #12

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5420. Min Act: -0.1700

Data Index: 7495191 (Open Web Text)

Max Activating Token Index: 978

Text #13

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5256. Min Act: -0.1700

Data Index: 475795 (Open Web Text)

Max Activating Token Index: 62

Text #14

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5156. Min Act: -0.1700

Data Index: 6065706 (Open Web Text)

Max Activating Token Index: 251

Text #15

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.4739. Min Act: -0.1700

Data Index: 862993 (Open Web Text)

Max Activating Token Index: 602

Text #16

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.4656. Min Act: -0.1700

Data Index: 6272969 (Open Web Text)

Max Activating Token Index: 246

Text #17

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.4590. Min Act: -0.1700

Data Index: 6406833 (Open Web Text)

Max Activating Token Index: 273

Text #18

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.4947. Min Act: -0.1700

Data Index: 1738553 (Open Web Text)

Max Activating Token Index: 400

Text #19

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.4737. Min Act: -0.1700

Data Index: 6531085 (Open Web Text)

Max Activating Token Index: 515