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

Dataset: Open Web Text

Neuron 3048 in Layer 3

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: 4.2312. Min Range: -4.2312

Max Act: 4.2312. Min Act: -0.1700

Data Index: 5576377 (Open Web Text)

Max Activating Token Index: 407

Text #1

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.2221. Min Act: -0.1700

Data Index: 2635379 (Open Web Text)

Max Activating Token Index: 968

Text #2

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.1997. Min Act: -0.1700

Data Index: 1235450 (Open Web Text)

Max Activating Token Index: 950

Text #3

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.1884. Min Act: -0.1700

Data Index: 3906128 (Open Web Text)

Max Activating Token Index: 124

Text #4

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.1651. Min Act: -0.1700

Data Index: 2328342 (Open Web Text)

Max Activating Token Index: 552

Text #5

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.1430. Min Act: -0.1700

Data Index: 8015221 (Open Web Text)

Max Activating Token Index: 140

Text #6

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.1269. Min Act: -0.1700

Data Index: 4515816 (Open Web Text)

Max Activating Token Index: 739

Text #7

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.1522. Min Act: -0.1700

Data Index: 434441 (Open Web Text)

Max Activating Token Index: 733

Text #8

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.0911. Min Act: -0.1700

Data Index: 2413334 (Open Web Text)

Max Activating Token Index: 434

Text #9

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.0766. Min Act: -0.1700

Data Index: 5384531 (Open Web Text)

Max Activating Token Index: 302

Text #10

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.0646. Min Act: -0.1700

Data Index: 5349508 (Open Web Text)

Max Activating Token Index: 683

Text #11

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.0787. Min Act: -0.1700

Data Index: 8134593 (Open Web Text)

Max Activating Token Index: 764

Text #12

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.0460. Min Act: -0.1700

Data Index: 7783616 (Open Web Text)

Max Activating Token Index: 602

Text #13

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.0413. Min Act: -0.1700

Data Index: 437323 (Open Web Text)

Max Activating Token Index: 992

Text #14

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.0642. Min Act: -0.1700

Data Index: 5325504 (Open Web Text)

Max Activating Token Index: 459

Text #15

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.0339. Min Act: -0.1700

Data Index: 5124120 (Open Web Text)

Max Activating Token Index: 440

Text #16

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.0651. Min Act: -0.1700

Data Index: 8222189 (Open Web Text)

Max Activating Token Index: 489

Text #17

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.0458. Min Act: -0.1700

Data Index: 6553658 (Open Web Text)

Max Activating Token Index: 90

Text #18

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.0150. Min Act: -0.1700

Data Index: 2708213 (Open Web Text)

Max Activating Token Index: 610

Text #19

Max Range: 4.2312. Min Range: -4.2312

Max Act: 4.0460. Min Act: -0.1700

Data Index: 8366326 (Open Web Text)

Max Activating Token Index: 303