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

Dataset: Open Web Text

Neuron 1578 in Layer 6

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: 5.2804. Min Range: -5.2804

Max Act: 5.2591. Min Act: -0.1700

Data Index: 6681739 (Open Web Text)

Max Activating Token Index: 427

Text #1

Max Range: 5.2804. Min Range: -5.2804

Max Act: 5.2804. Min Act: -0.1700

Data Index: 6905194 (Open Web Text)

Max Activating Token Index: 1004

Text #2

Max Range: 5.2804. Min Range: -5.2804

Max Act: 5.2503. Min Act: -0.1700

Data Index: 5845266 (Open Web Text)

Max Activating Token Index: 906

Text #3

Max Range: 5.2804. Min Range: -5.2804

Max Act: 5.2316. Min Act: -0.1700

Data Index: 4005774 (Open Web Text)

Max Activating Token Index: 253

Text #4

Max Range: 5.2804. Min Range: -5.2804

Max Act: 5.0955. Min Act: -0.1700

Data Index: 3900939 (Open Web Text)

Max Activating Token Index: 194

Text #5

Max Range: 5.2804. Min Range: -5.2804

Max Act: 5.0760. Min Act: -0.1700

Data Index: 1063534 (Open Web Text)

Max Activating Token Index: 810

Text #6

Max Range: 5.2804. Min Range: -5.2804

Max Act: 5.0983. Min Act: -0.1700

Data Index: 3849974 (Open Web Text)

Max Activating Token Index: 838

Text #7

Max Range: 5.2804. Min Range: -5.2804

Max Act: 5.0550. Min Act: -0.1700

Data Index: 7226820 (Open Web Text)

Max Activating Token Index: 498

Text #8

Max Range: 5.2804. Min Range: -5.2804

Max Act: 5.0826. Min Act: -0.1700

Data Index: 7282739 (Open Web Text)

Max Activating Token Index: 325

Text #9

Max Range: 5.2804. Min Range: -5.2804

Max Act: 5.0311. Min Act: -0.1700

Data Index: 7472941 (Open Web Text)

Max Activating Token Index: 671

Text #10

Max Range: 5.2804. Min Range: -5.2804

Max Act: 5.0170. Min Act: -0.1700

Data Index: 6733664 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 5.2804. Min Range: -5.2804

Max Act: 4.9936. Min Act: -0.1700

Data Index: 1252114 (Open Web Text)

Max Activating Token Index: 528

Text #12

Max Range: 5.2804. Min Range: -5.2804

Max Act: 5.0112. Min Act: -0.1700

Data Index: 1674580 (Open Web Text)

Max Activating Token Index: 551

Text #13

Max Range: 5.2804. Min Range: -5.2804

Max Act: 4.9465. Min Act: -0.1700

Data Index: 4600553 (Open Web Text)

Max Activating Token Index: 910

Text #14

Max Range: 5.2804. Min Range: -5.2804

Max Act: 4.9531. Min Act: -0.1700

Data Index: 2135142 (Open Web Text)

Max Activating Token Index: 587

Text #15

Max Range: 5.2804. Min Range: -5.2804

Max Act: 4.9840. Min Act: -0.1700

Data Index: 8741087 (Open Web Text)

Max Activating Token Index: 162

Text #16

Max Range: 5.2804. Min Range: -5.2804

Max Act: 4.9454. Min Act: -0.1700

Data Index: 5870901 (Open Web Text)

Max Activating Token Index: 920

Text #17

Max Range: 5.2804. Min Range: -5.2804

Max Act: 4.8787. Min Act: -0.1700

Data Index: 3918249 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 5.2804. Min Range: -5.2804

Max Act: 4.9247. Min Act: -0.1700

Data Index: 6857490 (Open Web Text)

Max Activating Token Index: 251

Text #19

Max Range: 5.2804. Min Range: -5.2804

Max Act: 4.9220. Min Act: -0.1700

Data Index: 3485835 (Open Web Text)

Max Activating Token Index: 287