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

Dataset: Open Web Text

Neuron 1981 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: 3.9262. Min Range: -3.9262

Max Act: 3.9262. Min Act: -0.1700

Data Index: 3838977 (Open Web Text)

Max Activating Token Index: 368

Text #1

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.9062. Min Act: -0.1700

Data Index: 4471857 (Open Web Text)

Max Activating Token Index: 289

Text #2

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.8724. Min Act: -0.1700

Data Index: 6796391 (Open Web Text)

Max Activating Token Index: 429

Text #3

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.8889. Min Act: -0.1700

Data Index: 4014396 (Open Web Text)

Max Activating Token Index: 754

Text #4

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.8040. Min Act: -0.1700

Data Index: 4814483 (Open Web Text)

Max Activating Token Index: 477

Text #5

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.8108. Min Act: -0.1700

Data Index: 1844709 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.8182. Min Act: -0.1700

Data Index: 7956471 (Open Web Text)

Max Activating Token Index: 965

Text #7

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.7587. Min Act: -0.1700

Data Index: 2824463 (Open Web Text)

Max Activating Token Index: 923

Text #8

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.8045. Min Act: -0.1700

Data Index: 767644 (Open Web Text)

Max Activating Token Index: 651

Text #9

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.7565. Min Act: -0.1700

Data Index: 7688091 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.7802. Min Act: -0.1700

Data Index: 7624464 (Open Web Text)

Max Activating Token Index: 416

Text #11

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.7840. Min Act: -0.1700

Data Index: 1450071 (Open Web Text)

Max Activating Token Index: 723

Text #12

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.7377. Min Act: -0.1700

Data Index: 2764504 (Open Web Text)

Max Activating Token Index: 583

Text #13

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.7397. Min Act: -0.1700

Data Index: 1450064 (Open Web Text)

Max Activating Token Index: 239

Text #14

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.7499. Min Act: -0.1700

Data Index: 148421 (Open Web Text)

Max Activating Token Index: 257

Text #15

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.7374. Min Act: -0.1700

Data Index: 6889354 (Open Web Text)

Max Activating Token Index: 1007

Text #16

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.6964. Min Act: -0.1700

Data Index: 6751534 (Open Web Text)

Max Activating Token Index: 753

Text #17

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.7076. Min Act: -0.1700

Data Index: 4097243 (Open Web Text)

Max Activating Token Index: 348

Text #18

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.7080. Min Act: -0.1700

Data Index: 6818261 (Open Web Text)

Max Activating Token Index: 112

Text #19

Max Range: 3.9262. Min Range: -3.9262

Max Act: 3.7157. Min Act: -0.1700

Data Index: 5253147 (Open Web Text)

Max Activating Token Index: 583