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

Dataset: Open Web Text

Neuron 655 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: 3.2354. Min Range: -3.2354

Max Act: 3.2354. Min Act: -0.1700

Data Index: 6749255 (Open Web Text)

Max Activating Token Index: 306

Text #1

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.2135. Min Act: -0.1700

Data Index: 562977 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.1906. Min Act: -0.1700

Data Index: 959309 (Open Web Text)

Max Activating Token Index: 712

Text #3

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.1743. Min Act: -0.1700

Data Index: 7673239 (Open Web Text)

Max Activating Token Index: 601

Text #4

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.1596. Min Act: -0.1700

Data Index: 3467173 (Open Web Text)

Max Activating Token Index: 972

Text #5

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.1216. Min Act: -0.1700

Data Index: 6958407 (Open Web Text)

Max Activating Token Index: 972

Text #6

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.1327. Min Act: -0.1700

Data Index: 1569825 (Open Web Text)

Max Activating Token Index: 184

Text #7

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0820. Min Act: -0.1700

Data Index: 84997 (Open Web Text)

Max Activating Token Index: 288

Text #8

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0861. Min Act: -0.1700

Data Index: 2249713 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0479. Min Act: -0.1700

Data Index: 4714276 (Open Web Text)

Max Activating Token Index: 39

Text #10

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0613. Min Act: -0.1700

Data Index: 7990392 (Open Web Text)

Max Activating Token Index: 440

Text #11

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0388. Min Act: -0.1700

Data Index: 6107993 (Open Web Text)

Max Activating Token Index: 648

Text #12

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0296. Min Act: -0.1700

Data Index: 5598593 (Open Web Text)

Max Activating Token Index: 418

Text #13

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0470. Min Act: -0.1700

Data Index: 1021413 (Open Web Text)

Max Activating Token Index: 618

Text #14

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0500. Min Act: -0.1700

Data Index: 7593939 (Open Web Text)

Max Activating Token Index: 103

Text #15

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0437. Min Act: -0.1700

Data Index: 2634052 (Open Web Text)

Max Activating Token Index: 710

Text #16

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0539. Min Act: -0.1700

Data Index: 7287623 (Open Web Text)

Max Activating Token Index: 85

Text #17

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0504. Min Act: -0.1700

Data Index: 4008240 (Open Web Text)

Max Activating Token Index: 132

Text #18

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0515. Min Act: -0.1700

Data Index: 6191612 (Open Web Text)

Max Activating Token Index: 932

Text #19

Max Range: 3.2354. Min Range: -3.2354

Max Act: 3.0336. Min Act: -0.1700

Data Index: 3376475 (Open Web Text)

Max Activating Token Index: 847