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

Dataset: Open Web Text

Neuron 1634 in Layer 2

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: 3.2822. Min Range: -3.2822

Max Act: 3.2822. Min Act: -0.1700

Data Index: 4569036 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.2691. Min Act: -0.1700

Data Index: 1311427 (Open Web Text)

Max Activating Token Index: 466

Text #2

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.2416. Min Act: -0.1700

Data Index: 6643162 (Open Web Text)

Max Activating Token Index: 267

Text #3

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.2338. Min Act: -0.1700

Data Index: 8304703 (Open Web Text)

Max Activating Token Index: 180

Text #4

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.1684. Min Act: -0.1700

Data Index: 3297398 (Open Web Text)

Max Activating Token Index: 925

Text #5

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.1932. Min Act: -0.1700

Data Index: 2646043 (Open Web Text)

Max Activating Token Index: 287

Text #6

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.1741. Min Act: -0.1700

Data Index: 6880752 (Open Web Text)

Max Activating Token Index: 664

Text #7

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.1463. Min Act: -0.1700

Data Index: 2319663 (Open Web Text)

Max Activating Token Index: 321

Text #8

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.1035. Min Act: -0.1700

Data Index: 1981859 (Open Web Text)

Max Activating Token Index: 369

Text #9

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.1488. Min Act: -0.1700

Data Index: 284874 (Open Web Text)

Max Activating Token Index: 254

Text #10

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.1538. Min Act: -0.1700

Data Index: 7654366 (Open Web Text)

Max Activating Token Index: 877

Text #11

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.1876. Min Act: -0.1700

Data Index: 941682 (Open Web Text)

Max Activating Token Index: 441

Text #12

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.1461. Min Act: -0.1700

Data Index: 6322099 (Open Web Text)

Max Activating Token Index: 534

Text #13

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.1202. Min Act: -0.1700

Data Index: 8171515 (Open Web Text)

Max Activating Token Index: 202

Text #14

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.0949. Min Act: -0.1700

Data Index: 2543651 (Open Web Text)

Max Activating Token Index: 194

Text #15

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.1362. Min Act: -0.1700

Data Index: 6741422 (Open Web Text)

Max Activating Token Index: 183

Text #16

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.0999. Min Act: -0.1700

Data Index: 3290951 (Open Web Text)

Max Activating Token Index: 148

Text #17

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.1224. Min Act: -0.1700

Data Index: 7328632 (Open Web Text)

Max Activating Token Index: 544

Text #18

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.0762. Min Act: -0.1700

Data Index: 5542500 (Open Web Text)

Max Activating Token Index: 1019

Text #19

Max Range: 3.2822. Min Range: -3.2822

Max Act: 3.0847. Min Act: -0.1700

Data Index: 1380123 (Open Web Text)

Max Activating Token Index: 127