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

Dataset: Open Web Text

Neuron 2507 in Layer 2

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: 2.6578. Min Range: -2.6578

Max Act: 2.6578. Min Act: -0.1700

Data Index: 5477806 (Open Web Text)

Max Activating Token Index: 473

Text #1

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5923. Min Act: -0.1700

Data Index: 5940551 (Open Web Text)

Max Activating Token Index: 233

Text #2

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5806. Min Act: -0.1700

Data Index: 7116064 (Open Web Text)

Max Activating Token Index: 195

Text #3

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5828. Min Act: -0.1700

Data Index: 2009909 (Open Web Text)

Max Activating Token Index: 382

Text #4

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5766. Min Act: -0.1700

Data Index: 5701471 (Open Web Text)

Max Activating Token Index: 842

Text #5

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5761. Min Act: -0.1700

Data Index: 4137548 (Open Web Text)

Max Activating Token Index: 398

Text #6

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5748. Min Act: -0.1700

Data Index: 7155785 (Open Web Text)

Max Activating Token Index: 660

Text #7

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5418. Min Act: -0.1700

Data Index: 7673785 (Open Web Text)

Max Activating Token Index: 997

Text #8

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5765. Min Act: -0.1700

Data Index: 7320465 (Open Web Text)

Max Activating Token Index: 508

Text #9

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5801. Min Act: -0.1700

Data Index: 5796378 (Open Web Text)

Max Activating Token Index: 337

Text #10

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5497. Min Act: -0.1700

Data Index: 1216746 (Open Web Text)

Max Activating Token Index: 147

Text #11

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5574. Min Act: -0.1700

Data Index: 7720708 (Open Web Text)

Max Activating Token Index: 510

Text #12

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5579. Min Act: -0.1700

Data Index: 256448 (Open Web Text)

Max Activating Token Index: 195

Text #13

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5398. Min Act: -0.1700

Data Index: 3098262 (Open Web Text)

Max Activating Token Index: 468

Text #14

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5435. Min Act: -0.1700

Data Index: 4824161 (Open Web Text)

Max Activating Token Index: 78

Text #15

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5497. Min Act: -0.1700

Data Index: 5567378 (Open Web Text)

Max Activating Token Index: 464

Text #16

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5240. Min Act: -0.1700

Data Index: 3109558 (Open Web Text)

Max Activating Token Index: 65

Text #17

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5505. Min Act: -0.1700

Data Index: 4539975 (Open Web Text)

Max Activating Token Index: 987

Text #18

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5385. Min Act: -0.1700

Data Index: 3750283 (Open Web Text)

Max Activating Token Index: 459

Text #19

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.5243. Min Act: -0.1700

Data Index: 1431116 (Open Web Text)

Max Activating Token Index: 542