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

Dataset: Open Web Text

Neuron 602 in Layer 1

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: 0.8920. Min Range: -0.8920

Max Act: 0.8920. Min Act: -0.1700

Data Index: 3286153 (Open Web Text)

Max Activating Token Index: 710

Text #1

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8811. Min Act: -0.1700

Data Index: 6489148 (Open Web Text)

Max Activating Token Index: 697

Text #2

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8722. Min Act: -0.1700

Data Index: 8343920 (Open Web Text)

Max Activating Token Index: 699

Text #3

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8824. Min Act: -0.1700

Data Index: 8479860 (Open Web Text)

Max Activating Token Index: 689

Text #4

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8590. Min Act: -0.1700

Data Index: 5780580 (Open Web Text)

Max Activating Token Index: 710

Text #5

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8352. Min Act: -0.1700

Data Index: 5141976 (Open Web Text)

Max Activating Token Index: 711

Text #6

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8443. Min Act: -0.1700

Data Index: 6028974 (Open Web Text)

Max Activating Token Index: 704

Text #7

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8251. Min Act: -0.1700

Data Index: 6106190 (Open Web Text)

Max Activating Token Index: 703

Text #8

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8193. Min Act: -0.1700

Data Index: 98502 (Open Web Text)

Max Activating Token Index: 702

Text #9

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8231. Min Act: -0.1700

Data Index: 7484653 (Open Web Text)

Max Activating Token Index: 701

Text #10

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8259. Min Act: -0.1700

Data Index: 992046 (Open Web Text)

Max Activating Token Index: 699

Text #11

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8127. Min Act: -0.1700

Data Index: 4310050 (Open Web Text)

Max Activating Token Index: 701

Text #12

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8207. Min Act: -0.1700

Data Index: 4678700 (Open Web Text)

Max Activating Token Index: 710

Text #13

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8299. Min Act: -0.1700

Data Index: 792093 (Open Web Text)

Max Activating Token Index: 692

Text #14

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8225. Min Act: -0.1700

Data Index: 4820585 (Open Web Text)

Max Activating Token Index: 703

Text #15

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8186. Min Act: -0.1700

Data Index: 2457229 (Open Web Text)

Max Activating Token Index: 710

Text #16

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8170. Min Act: -0.1700

Data Index: 3167017 (Open Web Text)

Max Activating Token Index: 691

Text #17

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8201. Min Act: -0.1700

Data Index: 4007214 (Open Web Text)

Max Activating Token Index: 164

Text #18

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8154. Min Act: -0.1700

Data Index: 5593533 (Open Web Text)

Max Activating Token Index: 705

Text #19

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8194. Min Act: -0.1700

Data Index: 2653319 (Open Web Text)

Max Activating Token Index: 696