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

Dataset: Open Web Text

Neuron 2591 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: 4.4251. Min Range: -4.4251

Max Act: 4.4112. Min Act: -0.1700

Data Index: 6443468 (Open Web Text)

Max Activating Token Index: 192

Text #1

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.4069. Min Act: -0.1700

Data Index: 1281344 (Open Web Text)

Max Activating Token Index: 107

Text #2

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.4251. Min Act: -0.1700

Data Index: 2906728 (Open Web Text)

Max Activating Token Index: 30

Text #3

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.3008. Min Act: -0.1700

Data Index: 8205622 (Open Web Text)

Max Activating Token Index: 793

Text #4

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.3268. Min Act: -0.1700

Data Index: 3333907 (Open Web Text)

Max Activating Token Index: 548

Text #5

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2631. Min Act: -0.1700

Data Index: 3404057 (Open Web Text)

Max Activating Token Index: 64

Text #6

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2237. Min Act: -0.1700

Data Index: 4493412 (Open Web Text)

Max Activating Token Index: 263

Text #7

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2383. Min Act: -0.1700

Data Index: 8824797 (Open Web Text)

Max Activating Token Index: 96

Text #8

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2568. Min Act: -0.1700

Data Index: 6291749 (Open Web Text)

Max Activating Token Index: 390

Text #9

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.1426. Min Act: -0.1700

Data Index: 8334868 (Open Web Text)

Max Activating Token Index: 773

Text #10

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.1474. Min Act: -0.1700

Data Index: 8460982 (Open Web Text)

Max Activating Token Index: 176

Text #11

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.1628. Min Act: -0.1700

Data Index: 5736227 (Open Web Text)

Max Activating Token Index: 834

Text #12

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.1505. Min Act: -0.1700

Data Index: 2921821 (Open Web Text)

Max Activating Token Index: 756

Text #13

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.1591. Min Act: -0.1700

Data Index: 589179 (Open Web Text)

Max Activating Token Index: 323

Text #14

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.1065. Min Act: -0.1700

Data Index: 3931109 (Open Web Text)

Max Activating Token Index: 507

Text #15

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.1563. Min Act: -0.1700

Data Index: 4221999 (Open Web Text)

Max Activating Token Index: 80

Text #16

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.1375. Min Act: -0.1700

Data Index: 692859 (Open Web Text)

Max Activating Token Index: 275

Text #17

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.0979. Min Act: -0.1700

Data Index: 7151025 (Open Web Text)

Max Activating Token Index: 184

Text #18

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.0772. Min Act: -0.1700

Data Index: 5987480 (Open Web Text)

Max Activating Token Index: 274

Text #19

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.1232. Min Act: -0.1700

Data Index: 8223171 (Open Web Text)

Max Activating Token Index: 466