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

Dataset: Open Web Text

Neuron 2197 in Layer 1

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: 1.5584. Min Range: -1.5584

Max Act: 1.5584. Min Act: -0.1700

Data Index: 8245722 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.5376. Min Act: -0.1700

Data Index: 6139016 (Open Web Text)

Max Activating Token Index: 582

Text #2

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.5346. Min Act: -0.1700

Data Index: 5817481 (Open Web Text)

Max Activating Token Index: 149

Text #3

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.5016. Min Act: -0.1700

Data Index: 5471751 (Open Web Text)

Max Activating Token Index: 218

Text #4

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.5099. Min Act: -0.1700

Data Index: 4835315 (Open Web Text)

Max Activating Token Index: 381

Text #5

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.5112. Min Act: -0.1700

Data Index: 1674594 (Open Web Text)

Max Activating Token Index: 208

Text #6

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.4947. Min Act: -0.1700

Data Index: 2350123 (Open Web Text)

Max Activating Token Index: 396

Text #7

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.4877. Min Act: -0.1700

Data Index: 1302440 (Open Web Text)

Max Activating Token Index: 446

Text #8

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.4911. Min Act: -0.1700

Data Index: 1766208 (Open Web Text)

Max Activating Token Index: 842

Text #9

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.4882. Min Act: -0.1700

Data Index: 751150 (Open Web Text)

Max Activating Token Index: 157

Text #10

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.4903. Min Act: -0.1700

Data Index: 7208643 (Open Web Text)

Max Activating Token Index: 376

Text #11

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.4879. Min Act: -0.1685

Data Index: 1766612 (Open Web Text)

Max Activating Token Index: 113

Text #12

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.4857. Min Act: -0.1700

Data Index: 6269586 (Open Web Text)

Max Activating Token Index: 73

Text #13

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.4816. Min Act: -0.1700

Data Index: 1459861 (Open Web Text)

Max Activating Token Index: 806

Text #14

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.4886. Min Act: -0.1695

Data Index: 6147864 (Open Web Text)

Max Activating Token Index: 306

Text #15

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.4733. Min Act: -0.1700

Data Index: 2356639 (Open Web Text)

Max Activating Token Index: 307

Text #16

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.4775. Min Act: -0.1700

Data Index: 8358821 (Open Web Text)

Max Activating Token Index: 267

Text #17

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.4812. Min Act: -0.1700

Data Index: 1766601 (Open Web Text)

Max Activating Token Index: 749

Text #18

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.4721. Min Act: -0.1700

Data Index: 4651889 (Open Web Text)

Max Activating Token Index: 135

Text #19

Max Range: 1.5584. Min Range: -1.5584

Max Act: 1.4805. Min Act: -0.1700

Data Index: 2169275 (Open Web Text)

Max Activating Token Index: 460