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

Dataset: Open Web Text

Neuron 2638 in Layer 6

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: 6.7430. Min Range: -6.7430

Max Act: 6.7430. Min Act: -0.1700

Data Index: 522037 (Open Web Text)

Max Activating Token Index: 712

Text #1

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.7347. Min Act: -0.1700

Data Index: 2129295 (Open Web Text)

Max Activating Token Index: 998

Text #2

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.7209. Min Act: -0.1700

Data Index: 2313253 (Open Web Text)

Max Activating Token Index: 439

Text #3

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.7278. Min Act: -0.1700

Data Index: 3760393 (Open Web Text)

Max Activating Token Index: 510

Text #4

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.6974. Min Act: -0.1700

Data Index: 3768513 (Open Web Text)

Max Activating Token Index: 436

Text #5

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.6895. Min Act: -0.1700

Data Index: 5955058 (Open Web Text)

Max Activating Token Index: 668

Text #6

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.6687. Min Act: -0.1700

Data Index: 3506952 (Open Web Text)

Max Activating Token Index: 689

Text #7

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.6899. Min Act: -0.1700

Data Index: 7042551 (Open Web Text)

Max Activating Token Index: 347

Text #8

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.6517. Min Act: -0.1700

Data Index: 447965 (Open Web Text)

Max Activating Token Index: 576

Text #9

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.6431. Min Act: -0.1700

Data Index: 6197040 (Open Web Text)

Max Activating Token Index: 835

Text #10

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.6136. Min Act: -0.1700

Data Index: 7220210 (Open Web Text)

Max Activating Token Index: 946

Text #11

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.6511. Min Act: -0.1700

Data Index: 7493699 (Open Web Text)

Max Activating Token Index: 60

Text #12

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.6176. Min Act: -0.1700

Data Index: 2176743 (Open Web Text)

Max Activating Token Index: 905

Text #13

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.6212. Min Act: -0.1700

Data Index: 6188994 (Open Web Text)

Max Activating Token Index: 275

Text #14

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.6358. Min Act: -0.1700

Data Index: 6782577 (Open Web Text)

Max Activating Token Index: 495

Text #15

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.6100. Min Act: -0.1700

Data Index: 4474678 (Open Web Text)

Max Activating Token Index: 142

Text #16

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.5915. Min Act: -0.1700

Data Index: 3404233 (Open Web Text)

Max Activating Token Index: 499

Text #17

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.6091. Min Act: -0.1700

Data Index: 6554270 (Open Web Text)

Max Activating Token Index: 478

Text #18

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.5866. Min Act: -0.1700

Data Index: 5041334 (Open Web Text)

Max Activating Token Index: 665

Text #19

Max Range: 6.7430. Min Range: -6.7430

Max Act: 6.6171. Min Act: -0.1700

Data Index: 7893537 (Open Web Text)

Max Activating Token Index: 283