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

Dataset: Open Web Text

Neuron 2515 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: 3.0840. Min Range: -3.0840

Max Act: 3.0840. Min Act: -0.1700

Data Index: 7246755 (Open Web Text)

Max Activating Token Index: 525

Text #1

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.9172. Min Act: -0.1700

Data Index: 4347126 (Open Web Text)

Max Activating Token Index: 66

Text #2

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.9020. Min Act: -0.1700

Data Index: 8539681 (Open Web Text)

Max Activating Token Index: 453

Text #3

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.8672. Min Act: -0.1700

Data Index: 6630420 (Open Web Text)

Max Activating Token Index: 468

Text #4

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.8501. Min Act: -0.1700

Data Index: 2982812 (Open Web Text)

Max Activating Token Index: 261

Text #5

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.8217. Min Act: -0.1700

Data Index: 5728474 (Open Web Text)

Max Activating Token Index: 325

Text #6

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.8329. Min Act: -0.1700

Data Index: 7560417 (Open Web Text)

Max Activating Token Index: 467

Text #7

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.7953. Min Act: -0.1700

Data Index: 1560431 (Open Web Text)

Max Activating Token Index: 765

Text #8

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.7870. Min Act: -0.1700

Data Index: 6082968 (Open Web Text)

Max Activating Token Index: 329

Text #9

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.7921. Min Act: -0.1700

Data Index: 1098125 (Open Web Text)

Max Activating Token Index: 922

Text #10

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.7846. Min Act: -0.1700

Data Index: 5874497 (Open Web Text)

Max Activating Token Index: 515

Text #11

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.7831. Min Act: -0.1700

Data Index: 8254995 (Open Web Text)

Max Activating Token Index: 734

Text #12

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.7668. Min Act: -0.1700

Data Index: 684876 (Open Web Text)

Max Activating Token Index: 492

Text #13

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.7296. Min Act: -0.1700

Data Index: 6876105 (Open Web Text)

Max Activating Token Index: 434

Text #14

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.7212. Min Act: -0.1700

Data Index: 7312671 (Open Web Text)

Max Activating Token Index: 147

Text #15

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.7382. Min Act: -0.1700

Data Index: 1165064 (Open Web Text)

Max Activating Token Index: 560

Text #16

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.7101. Min Act: -0.1700

Data Index: 8743531 (Open Web Text)

Max Activating Token Index: 573

Text #17

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.7262. Min Act: -0.1700

Data Index: 4345306 (Open Web Text)

Max Activating Token Index: 946

Text #18

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.7275. Min Act: -0.1700

Data Index: 5068548 (Open Web Text)

Max Activating Token Index: 572

Text #19

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.7370. Min Act: -0.1700

Data Index: 6578912 (Open Web Text)

Max Activating Token Index: 341