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

Dataset: Open Web Text

Neuron 1977 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: 3.2558. Min Range: -3.2558

Max Act: 3.2333. Min Act: -0.1700

Data Index: 3391392 (Open Web Text)

Max Activating Token Index: 465

Text #1

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.2422. Min Act: -0.1700

Data Index: 1018213 (Open Web Text)

Max Activating Token Index: 964

Text #2

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.2503. Min Act: -0.1700

Data Index: 3220090 (Open Web Text)

Max Activating Token Index: 639

Text #3

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.2558. Min Act: -0.1700

Data Index: 7331734 (Open Web Text)

Max Activating Token Index: 610

Text #4

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.2181. Min Act: -0.1700

Data Index: 7422112 (Open Web Text)

Max Activating Token Index: 911

Text #5

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.2329. Min Act: -0.1700

Data Index: 1756770 (Open Web Text)

Max Activating Token Index: 213

Text #6

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.2139. Min Act: -0.1700

Data Index: 3886240 (Open Web Text)

Max Activating Token Index: 52

Text #7

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.2186. Min Act: -0.1700

Data Index: 6732267 (Open Web Text)

Max Activating Token Index: 79

Text #8

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.2031. Min Act: -0.1700

Data Index: 2555485 (Open Web Text)

Max Activating Token Index: 291

Text #9

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.1990. Min Act: -0.1700

Data Index: 4957793 (Open Web Text)

Max Activating Token Index: 796

Text #10

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.1841. Min Act: -0.1700

Data Index: 2852241 (Open Web Text)

Max Activating Token Index: 620

Text #11

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.1708. Min Act: -0.1700

Data Index: 2530236 (Open Web Text)

Max Activating Token Index: 313

Text #12

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.1757. Min Act: -0.1700

Data Index: 6032362 (Open Web Text)

Max Activating Token Index: 166

Text #13

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.1526. Min Act: -0.1700

Data Index: 8568027 (Open Web Text)

Max Activating Token Index: 494

Text #14

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.1529. Min Act: -0.1700

Data Index: 2871343 (Open Web Text)

Max Activating Token Index: 482

Text #15

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.1752. Min Act: -0.1700

Data Index: 6499420 (Open Web Text)

Max Activating Token Index: 803

Text #16

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.1550. Min Act: -0.1700

Data Index: 2130289 (Open Web Text)

Max Activating Token Index: 300

Text #17

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.1718. Min Act: -0.1700

Data Index: 4677019 (Open Web Text)

Max Activating Token Index: 395

Text #18

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.1763. Min Act: -0.1700

Data Index: 4794657 (Open Web Text)

Max Activating Token Index: 771

Text #19

Max Range: 3.2558. Min Range: -3.2558

Max Act: 3.1358. Min Act: -0.1700

Data Index: 5797781 (Open Web Text)

Max Activating Token Index: 329