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

Dataset: Open Web Text

Neuron 1166 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: 1.5061. Min Range: -1.5061

Max Act: 1.5061. Min Act: -0.1700

Data Index: 6374865 (Open Web Text)

Max Activating Token Index: 79

Text #1

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4984. Min Act: -0.1700

Data Index: 4564037 (Open Web Text)

Max Activating Token Index: 45

Text #2

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4850. Min Act: -0.1700

Data Index: 2946366 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4771. Min Act: -0.1700

Data Index: 6875547 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4735. Min Act: -0.1700

Data Index: 7867376 (Open Web Text)

Max Activating Token Index: 24

Text #5

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4658. Min Act: -0.1700

Data Index: 6402261 (Open Web Text)

Max Activating Token Index: 311

Text #6

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4551. Min Act: -0.1700

Data Index: 1387682 (Open Web Text)

Max Activating Token Index: 733

Text #7

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4579. Min Act: -0.1700

Data Index: 4167212 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4540. Min Act: -0.1699

Data Index: 3160004 (Open Web Text)

Max Activating Token Index: 631

Text #9

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4560. Min Act: -0.1700

Data Index: 4589571 (Open Web Text)

Max Activating Token Index: 225

Text #10

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4559. Min Act: -0.1700

Data Index: 8329075 (Open Web Text)

Max Activating Token Index: 832

Text #11

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4506. Min Act: -0.1700

Data Index: 4070293 (Open Web Text)

Max Activating Token Index: 83

Text #12

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4480. Min Act: -0.1700

Data Index: 6935201 (Open Web Text)

Max Activating Token Index: 18

Text #13

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4422. Min Act: -0.1700

Data Index: 8148754 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4424. Min Act: -0.1700

Data Index: 1156881 (Open Web Text)

Max Activating Token Index: 251

Text #15

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4343. Min Act: -0.1698

Data Index: 3634986 (Open Web Text)

Max Activating Token Index: 830

Text #16

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4330. Min Act: -0.1700

Data Index: 7272918 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4355. Min Act: -0.1700

Data Index: 1766419 (Open Web Text)

Max Activating Token Index: 252

Text #18

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4361. Min Act: -0.1700

Data Index: 336413 (Open Web Text)

Max Activating Token Index: 58

Text #19

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4385. Min Act: -0.1700

Data Index: 6719511 (Open Web Text)

Max Activating Token Index: 20