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

Dataset: Open Web Text

Neuron 2823 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: 4.8091. Min Range: -4.8091

Max Act: 4.8091. Min Act: -0.1700

Data Index: 4617847 (Open Web Text)

Max Activating Token Index: 739

Text #1

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.7156. Min Act: -0.1700

Data Index: 8112375 (Open Web Text)

Max Activating Token Index: 788

Text #2

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.6520. Min Act: -0.1700

Data Index: 7461504 (Open Web Text)

Max Activating Token Index: 822

Text #3

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.6367. Min Act: -0.1700

Data Index: 6893666 (Open Web Text)

Max Activating Token Index: 991

Text #4

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.5666. Min Act: -0.1700

Data Index: 2052992 (Open Web Text)

Max Activating Token Index: 771

Text #5

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.5415. Min Act: -0.1700

Data Index: 6912168 (Open Web Text)

Max Activating Token Index: 549

Text #6

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.5495. Min Act: -0.1700

Data Index: 2837021 (Open Web Text)

Max Activating Token Index: 529

Text #7

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.5226. Min Act: -0.1700

Data Index: 7111365 (Open Web Text)

Max Activating Token Index: 472

Text #8

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.5050. Min Act: -0.1700

Data Index: 4903211 (Open Web Text)

Max Activating Token Index: 747

Text #9

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.5364. Min Act: -0.1700

Data Index: 7879525 (Open Web Text)

Max Activating Token Index: 816

Text #10

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.5603. Min Act: -0.1700

Data Index: 5374046 (Open Web Text)

Max Activating Token Index: 496

Text #11

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.4973. Min Act: -0.1700

Data Index: 3751471 (Open Web Text)

Max Activating Token Index: 410

Text #12

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.4697. Min Act: -0.1700

Data Index: 1631959 (Open Web Text)

Max Activating Token Index: 821

Text #13

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.4492. Min Act: -0.1700

Data Index: 8068806 (Open Web Text)

Max Activating Token Index: 552

Text #14

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.4488. Min Act: -0.1700

Data Index: 3365898 (Open Web Text)

Max Activating Token Index: 829

Text #15

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.4464. Min Act: -0.1700

Data Index: 6013012 (Open Web Text)

Max Activating Token Index: 24

Text #16

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.4392. Min Act: -0.1700

Data Index: 1031065 (Open Web Text)

Max Activating Token Index: 339

Text #17

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.4047. Min Act: -0.1700

Data Index: 4158180 (Open Web Text)

Max Activating Token Index: 791

Text #18

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.4076. Min Act: -0.1700

Data Index: 7303787 (Open Web Text)

Max Activating Token Index: 516

Text #19

Max Range: 4.8091. Min Range: -4.8091

Max Act: 4.4195. Min Act: -0.1700

Data Index: 4517729 (Open Web Text)

Max Activating Token Index: 395