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

Dataset: Open Web Text

Neuron 2762 in Layer 4

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: 3.0545. Min Range: -3.0545

Max Act: 3.0545. Min Act: -0.1700

Data Index: 390442 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 3.0545. Min Range: -3.0545

Max Act: 3.0245. Min Act: -0.1700

Data Index: 4287656 (Open Web Text)

Max Activating Token Index: 771

Text #2

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.9955. Min Act: -0.1700

Data Index: 7258313 (Open Web Text)

Max Activating Token Index: 675

Text #3

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.9956. Min Act: -0.1700

Data Index: 4996034 (Open Web Text)

Max Activating Token Index: 711

Text #4

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.9841. Min Act: -0.1700

Data Index: 5767831 (Open Web Text)

Max Activating Token Index: 755

Text #5

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.9309. Min Act: -0.1700

Data Index: 3604376 (Open Web Text)

Max Activating Token Index: 483

Text #6

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.8895. Min Act: -0.1700

Data Index: 6825133 (Open Web Text)

Max Activating Token Index: 938

Text #7

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.9367. Min Act: -0.1700

Data Index: 7172476 (Open Web Text)

Max Activating Token Index: 946

Text #8

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.9204. Min Act: -0.1700

Data Index: 4679233 (Open Web Text)

Max Activating Token Index: 1016

Text #9

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.9212. Min Act: -0.1700

Data Index: 2060372 (Open Web Text)

Max Activating Token Index: 848

Text #10

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.9136. Min Act: -0.1700

Data Index: 1974396 (Open Web Text)

Max Activating Token Index: 422

Text #11

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.9104. Min Act: -0.1700

Data Index: 2273083 (Open Web Text)

Max Activating Token Index: 517

Text #12

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.8952. Min Act: -0.1700

Data Index: 4957972 (Open Web Text)

Max Activating Token Index: 1001

Text #13

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.8834. Min Act: -0.1700

Data Index: 7256136 (Open Web Text)

Max Activating Token Index: 815

Text #14

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.9033. Min Act: -0.1700

Data Index: 5278949 (Open Web Text)

Max Activating Token Index: 455

Text #15

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.8641. Min Act: -0.1700

Data Index: 1995015 (Open Web Text)

Max Activating Token Index: 629

Text #16

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.8724. Min Act: -0.1700

Data Index: 4150181 (Open Web Text)

Max Activating Token Index: 537

Text #17

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.8853. Min Act: -0.1700

Data Index: 2279465 (Open Web Text)

Max Activating Token Index: 901

Text #18

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.8555. Min Act: -0.1700

Data Index: 4943121 (Open Web Text)

Max Activating Token Index: 939

Text #19

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.8773. Min Act: -0.1700

Data Index: 5050082 (Open Web Text)

Max Activating Token Index: 397