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

Dataset: Open Web Text

Neuron 1308 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: 3.9775. Min Range: -3.9775

Max Act: 3.9775. Min Act: -0.1700

Data Index: 4180532 (Open Web Text)

Max Activating Token Index: 868

Text #1

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.9009. Min Act: -0.1700

Data Index: 5566040 (Open Web Text)

Max Activating Token Index: 40

Text #2

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.9098. Min Act: -0.1700

Data Index: 8095840 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8901. Min Act: -0.1700

Data Index: 2928547 (Open Web Text)

Max Activating Token Index: 754

Text #4

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8818. Min Act: -0.1700

Data Index: 3349480 (Open Web Text)

Max Activating Token Index: 949

Text #5

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8955. Min Act: -0.1700

Data Index: 1731610 (Open Web Text)

Max Activating Token Index: 584

Text #6

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8673. Min Act: -0.1700

Data Index: 8522391 (Open Web Text)

Max Activating Token Index: 177

Text #7

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8553. Min Act: -0.1700

Data Index: 3035568 (Open Web Text)

Max Activating Token Index: 908

Text #8

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8488. Min Act: -0.1700

Data Index: 4779743 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8553. Min Act: -0.1700

Data Index: 3918831 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8409. Min Act: -0.1700

Data Index: 4896211 (Open Web Text)

Max Activating Token Index: 882

Text #11

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8454. Min Act: -0.1700

Data Index: 7164609 (Open Web Text)

Max Activating Token Index: 443

Text #12

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8166. Min Act: -0.1700

Data Index: 2074037 (Open Web Text)

Max Activating Token Index: 513

Text #13

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8214. Min Act: -0.1700

Data Index: 5091811 (Open Web Text)

Max Activating Token Index: 992

Text #14

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8171. Min Act: -0.1700

Data Index: 424749 (Open Web Text)

Max Activating Token Index: 824

Text #15

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8158. Min Act: -0.1700

Data Index: 2283362 (Open Web Text)

Max Activating Token Index: 1006

Text #16

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8038. Min Act: -0.1700

Data Index: 5277833 (Open Web Text)

Max Activating Token Index: 782

Text #17

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8356. Min Act: -0.1700

Data Index: 5369817 (Open Web Text)

Max Activating Token Index: 588

Text #18

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8109. Min Act: -0.1700

Data Index: 2607353 (Open Web Text)

Max Activating Token Index: 1006

Text #19

Max Range: 3.9775. Min Range: -3.9775

Max Act: 3.8231. Min Act: -0.1700

Data Index: 3879822 (Open Web Text)

Max Activating Token Index: 93