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

Dataset: Open Web Text

Neuron 2255 in Layer 4

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: 4.1831. Min Range: -4.1831

Max Act: 4.1831. Min Act: -0.1700

Data Index: 3137061 (Open Web Text)

Max Activating Token Index: 115

Text #1

Max Range: 4.1831. Min Range: -4.1831

Max Act: 4.0965. Min Act: -0.1700

Data Index: 4538381 (Open Web Text)

Max Activating Token Index: 308

Text #2

Max Range: 4.1831. Min Range: -4.1831

Max Act: 4.0847. Min Act: -0.1700

Data Index: 4163981 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 4.1831. Min Range: -4.1831

Max Act: 4.0787. Min Act: -0.1700

Data Index: 6582296 (Open Web Text)

Max Activating Token Index: 19

Text #4

Max Range: 4.1831. Min Range: -4.1831

Max Act: 4.0528. Min Act: -0.1700

Data Index: 4099553 (Open Web Text)

Max Activating Token Index: 176

Text #5

Max Range: 4.1831. Min Range: -4.1831

Max Act: 4.0306. Min Act: -0.1700

Data Index: 8603485 (Open Web Text)

Max Activating Token Index: 350

Text #6

Max Range: 4.1831. Min Range: -4.1831

Max Act: 4.0391. Min Act: -0.1700

Data Index: 6878232 (Open Web Text)

Max Activating Token Index: 62

Text #7

Max Range: 4.1831. Min Range: -4.1831

Max Act: 4.0255. Min Act: -0.1700

Data Index: 6421562 (Open Web Text)

Max Activating Token Index: 524

Text #8

Max Range: 4.1831. Min Range: -4.1831

Max Act: 4.0254. Min Act: -0.1700

Data Index: 2943387 (Open Web Text)

Max Activating Token Index: 54

Text #9

Max Range: 4.1831. Min Range: -4.1831

Max Act: 3.9984. Min Act: -0.1700

Data Index: 2348880 (Open Web Text)

Max Activating Token Index: 316

Text #10

Max Range: 4.1831. Min Range: -4.1831

Max Act: 3.9799. Min Act: -0.1700

Data Index: 8335509 (Open Web Text)

Max Activating Token Index: 561

Text #11

Max Range: 4.1831. Min Range: -4.1831

Max Act: 4.0040. Min Act: -0.1700

Data Index: 1050559 (Open Web Text)

Max Activating Token Index: 469

Text #12

Max Range: 4.1831. Min Range: -4.1831

Max Act: 3.9650. Min Act: -0.1700

Data Index: 8078350 (Open Web Text)

Max Activating Token Index: 875

Text #13

Max Range: 4.1831. Min Range: -4.1831

Max Act: 3.9668. Min Act: -0.1700

Data Index: 6872349 (Open Web Text)

Max Activating Token Index: 910

Text #14

Max Range: 4.1831. Min Range: -4.1831

Max Act: 3.9838. Min Act: -0.1700

Data Index: 103701 (Open Web Text)

Max Activating Token Index: 396

Text #15

Max Range: 4.1831. Min Range: -4.1831

Max Act: 3.9672. Min Act: -0.1700

Data Index: 6604370 (Open Web Text)

Max Activating Token Index: 958

Text #16

Max Range: 4.1831. Min Range: -4.1831

Max Act: 3.9609. Min Act: -0.1700

Data Index: 7513834 (Open Web Text)

Max Activating Token Index: 362

Text #17

Max Range: 4.1831. Min Range: -4.1831

Max Act: 3.9561. Min Act: -0.1700

Data Index: 1031630 (Open Web Text)

Max Activating Token Index: 566

Text #18

Max Range: 4.1831. Min Range: -4.1831

Max Act: 3.9475. Min Act: -0.1700

Data Index: 5062577 (Open Web Text)

Max Activating Token Index: 205

Text #19

Max Range: 4.1831. Min Range: -4.1831

Max Act: 3.9377. Min Act: -0.1700

Data Index: 6580526 (Open Web Text)

Max Activating Token Index: 58