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

Dataset: Open Web Text

Neuron 2254 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: 4.3005. Min Range: -4.3005

Max Act: 4.3005. Min Act: -0.1700

Data Index: 5586965 (Open Web Text)

Max Activating Token Index: 589

Text #1

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.2591. Min Act: -0.1700

Data Index: 5996703 (Open Web Text)

Max Activating Token Index: 1000

Text #2

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.2052. Min Act: -0.1700

Data Index: 3028903 (Open Web Text)

Max Activating Token Index: 647

Text #3

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1750. Min Act: -0.1700

Data Index: 2517047 (Open Web Text)

Max Activating Token Index: 793

Text #4

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1813. Min Act: -0.1700

Data Index: 5628492 (Open Web Text)

Max Activating Token Index: 798

Text #5

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1808. Min Act: -0.1700

Data Index: 6289771 (Open Web Text)

Max Activating Token Index: 382

Text #6

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1908. Min Act: -0.1700

Data Index: 3855406 (Open Web Text)

Max Activating Token Index: 489

Text #7

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1568. Min Act: -0.1700

Data Index: 3298171 (Open Web Text)

Max Activating Token Index: 222

Text #8

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1887. Min Act: -0.1700

Data Index: 1888198 (Open Web Text)

Max Activating Token Index: 383

Text #9

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1927. Min Act: -0.1700

Data Index: 599802 (Open Web Text)

Max Activating Token Index: 735

Text #10

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1586. Min Act: -0.1700

Data Index: 4149114 (Open Web Text)

Max Activating Token Index: 91

Text #11

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1628. Min Act: -0.1700

Data Index: 1223811 (Open Web Text)

Max Activating Token Index: 455

Text #12

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1454. Min Act: -0.1700

Data Index: 2348520 (Open Web Text)

Max Activating Token Index: 709

Text #13

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1517. Min Act: -0.1700

Data Index: 5863583 (Open Web Text)

Max Activating Token Index: 825

Text #14

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1433. Min Act: -0.1700

Data Index: 3161503 (Open Web Text)

Max Activating Token Index: 637

Text #15

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1617. Min Act: -0.1700

Data Index: 2390412 (Open Web Text)

Max Activating Token Index: 869

Text #16

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1513. Min Act: -0.1700

Data Index: 394841 (Open Web Text)

Max Activating Token Index: 346

Text #17

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.0986. Min Act: -0.1700

Data Index: 4767900 (Open Web Text)

Max Activating Token Index: 719

Text #18

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1256. Min Act: -0.1700

Data Index: 71678 (Open Web Text)

Max Activating Token Index: 535

Text #19

Max Range: 4.3005. Min Range: -4.3005

Max Act: 4.1184. Min Act: -0.1700

Data Index: 5645638 (Open Web Text)

Max Activating Token Index: 321