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

Dataset: Open Web Text

Neuron 2840 in Layer 5

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: 4.5975. Min Range: -4.5975

Max Act: 4.5975. Min Act: -0.1700

Data Index: 650163 (Open Web Text)

Max Activating Token Index: 542

Text #1

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.3989. Min Act: -0.1700

Data Index: 1302093 (Open Web Text)

Max Activating Token Index: 686

Text #2

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.3691. Min Act: -0.1700

Data Index: 8550321 (Open Web Text)

Max Activating Token Index: 785

Text #3

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.3109. Min Act: -0.1700

Data Index: 5661353 (Open Web Text)

Max Activating Token Index: 249

Text #4

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.2880. Min Act: -0.1700

Data Index: 6434853 (Open Web Text)

Max Activating Token Index: 170

Text #5

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.2940. Min Act: -0.1700

Data Index: 6773949 (Open Web Text)

Max Activating Token Index: 106

Text #6

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.2638. Min Act: -0.1700

Data Index: 4894812 (Open Web Text)

Max Activating Token Index: 822

Text #7

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.2591. Min Act: -0.1700

Data Index: 7128728 (Open Web Text)

Max Activating Token Index: 32

Text #8

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.2488. Min Act: -0.1700

Data Index: 6234187 (Open Web Text)

Max Activating Token Index: 21

Text #9

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.2269. Min Act: -0.1700

Data Index: 1352367 (Open Web Text)

Max Activating Token Index: 631

Text #10

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.1839. Min Act: -0.1700

Data Index: 3545054 (Open Web Text)

Max Activating Token Index: 893

Text #11

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.1494. Min Act: -0.1700

Data Index: 7863981 (Open Web Text)

Max Activating Token Index: 587

Text #12

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.1727. Min Act: -0.1700

Data Index: 7971440 (Open Web Text)

Max Activating Token Index: 467

Text #13

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.1597. Min Act: -0.1700

Data Index: 3547852 (Open Web Text)

Max Activating Token Index: 128

Text #14

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.1492. Min Act: -0.1700

Data Index: 8498270 (Open Web Text)

Max Activating Token Index: 175

Text #15

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.2140. Min Act: -0.1700

Data Index: 4984550 (Open Web Text)

Max Activating Token Index: 666

Text #16

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.1798. Min Act: -0.1700

Data Index: 3037119 (Open Web Text)

Max Activating Token Index: 844

Text #17

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.1894. Min Act: -0.1700

Data Index: 513610 (Open Web Text)

Max Activating Token Index: 798

Text #18

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.1327. Min Act: -0.1700

Data Index: 1090863 (Open Web Text)

Max Activating Token Index: 569

Text #19

Max Range: 4.5975. Min Range: -4.5975

Max Act: 4.1161. Min Act: -0.1700

Data Index: 6397643 (Open Web Text)

Max Activating Token Index: 692