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

Dataset: Open Web Text

Neuron 3012 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: 4.3941. Min Range: -4.3941

Max Act: 4.3815. Min Act: -0.1700

Data Index: 912333 (Open Web Text)

Max Activating Token Index: 708

Text #1

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.3526. Min Act: -0.1700

Data Index: 1010920 (Open Web Text)

Max Activating Token Index: 398

Text #2

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.3406. Min Act: -0.1700

Data Index: 5598166 (Open Web Text)

Max Activating Token Index: 263

Text #3

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.3941. Min Act: -0.1700

Data Index: 6016658 (Open Web Text)

Max Activating Token Index: 923

Text #4

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.2675. Min Act: -0.1700

Data Index: 4137646 (Open Web Text)

Max Activating Token Index: 296

Text #5

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.3020. Min Act: -0.1700

Data Index: 3646419 (Open Web Text)

Max Activating Token Index: 1009

Text #6

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.2406. Min Act: -0.1700

Data Index: 4656190 (Open Web Text)

Max Activating Token Index: 318

Text #7

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.2797. Min Act: -0.1700

Data Index: 4978123 (Open Web Text)

Max Activating Token Index: 342

Text #8

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.2468. Min Act: -0.1700

Data Index: 3901304 (Open Web Text)

Max Activating Token Index: 748

Text #9

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.2818. Min Act: -0.1700

Data Index: 3907851 (Open Web Text)

Max Activating Token Index: 689

Text #10

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.2390. Min Act: -0.1700

Data Index: 5524520 (Open Web Text)

Max Activating Token Index: 801

Text #11

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.2382. Min Act: -0.1700

Data Index: 3283591 (Open Web Text)

Max Activating Token Index: 654

Text #12

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.2475. Min Act: -0.1700

Data Index: 7161618 (Open Web Text)

Max Activating Token Index: 229

Text #13

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.2047. Min Act: -0.1700

Data Index: 2871547 (Open Web Text)

Max Activating Token Index: 440

Text #14

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.1879. Min Act: -0.1700

Data Index: 4839609 (Open Web Text)

Max Activating Token Index: 382

Text #15

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.2091. Min Act: -0.1700

Data Index: 6064706 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.2083. Min Act: -0.1700

Data Index: 5185519 (Open Web Text)

Max Activating Token Index: 593

Text #17

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.2193. Min Act: -0.1700

Data Index: 220577 (Open Web Text)

Max Activating Token Index: 458

Text #18

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.2068. Min Act: -0.1700

Data Index: 874391 (Open Web Text)

Max Activating Token Index: 826

Text #19

Max Range: 4.3941. Min Range: -4.3941

Max Act: 4.1878. Min Act: -0.1700

Data Index: 8604035 (Open Web Text)

Max Activating Token Index: 298