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

Dataset: Open Web Text

Neuron 2914 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: 4.5710. Min Range: -4.5710

Max Act: 4.5710. Min Act: -0.1700

Data Index: 3316562 (Open Web Text)

Max Activating Token Index: 109

Text #1

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.2503. Min Act: -0.1700

Data Index: 3471016 (Open Web Text)

Max Activating Token Index: 605

Text #2

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.2899. Min Act: -0.1700

Data Index: 544940 (Open Web Text)

Max Activating Token Index: 1011

Text #3

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.1821. Min Act: -0.1700

Data Index: 7772181 (Open Web Text)

Max Activating Token Index: 519

Text #4

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.2039. Min Act: -0.1700

Data Index: 5899813 (Open Web Text)

Max Activating Token Index: 582

Text #5

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.1926. Min Act: -0.1700

Data Index: 4876849 (Open Web Text)

Max Activating Token Index: 420

Text #6

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.1749. Min Act: -0.1700

Data Index: 319352 (Open Web Text)

Max Activating Token Index: 226

Text #7

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.0902. Min Act: -0.1700

Data Index: 319343 (Open Web Text)

Max Activating Token Index: 818

Text #8

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.1558. Min Act: -0.1700

Data Index: 2798914 (Open Web Text)

Max Activating Token Index: 700

Text #9

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.1097. Min Act: -0.1700

Data Index: 8049611 (Open Web Text)

Max Activating Token Index: 620

Text #10

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.0692. Min Act: -0.1700

Data Index: 1624973 (Open Web Text)

Max Activating Token Index: 108

Text #11

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.0217. Min Act: -0.1700

Data Index: 8449740 (Open Web Text)

Max Activating Token Index: 706

Text #12

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.0577. Min Act: -0.1700

Data Index: 5621791 (Open Web Text)

Max Activating Token Index: 413

Text #13

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.0831. Min Act: -0.1700

Data Index: 1624972 (Open Web Text)

Max Activating Token Index: 757

Text #14

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.0445. Min Act: -0.1700

Data Index: 2856326 (Open Web Text)

Max Activating Token Index: 215

Text #15

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.0232. Min Act: -0.1700

Data Index: 7660213 (Open Web Text)

Max Activating Token Index: 927

Text #16

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.0236. Min Act: -0.1700

Data Index: 8749859 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.0422. Min Act: -0.1700

Data Index: 7860027 (Open Web Text)

Max Activating Token Index: 847

Text #18

Max Range: 4.5710. Min Range: -4.5710

Max Act: 4.0297. Min Act: -0.1700

Data Index: 7304772 (Open Web Text)

Max Activating Token Index: 438

Text #19

Max Range: 4.5710. Min Range: -4.5710

Max Act: 3.9825. Min Act: -0.1700

Data Index: 4262007 (Open Web Text)

Max Activating Token Index: 975