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

Dataset: Open Web Text

Neuron 871 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: 1.6842. Min Range: -1.6842

Max Act: 1.6842. Min Act: -0.1700

Data Index: 4483353 (Open Web Text)

Max Activating Token Index: 535

Text #1

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6651. Min Act: -0.1700

Data Index: 2932903 (Open Web Text)

Max Activating Token Index: 163

Text #2

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6633. Min Act: -0.1700

Data Index: 7477765 (Open Web Text)

Max Activating Token Index: 701

Text #3

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6618. Min Act: -0.1700

Data Index: 4455529 (Open Web Text)

Max Activating Token Index: 979

Text #4

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6582. Min Act: -0.1698

Data Index: 4789751 (Open Web Text)

Max Activating Token Index: 739

Text #5

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6556. Min Act: -0.1700

Data Index: 6401803 (Open Web Text)

Max Activating Token Index: 946

Text #6

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6610. Min Act: -0.1698

Data Index: 5134446 (Open Web Text)

Max Activating Token Index: 1001

Text #7

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6536. Min Act: -0.1700

Data Index: 5622080 (Open Web Text)

Max Activating Token Index: 944

Text #8

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6435. Min Act: -0.1700

Data Index: 5441141 (Open Web Text)

Max Activating Token Index: 303

Text #9

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6552. Min Act: -0.1699

Data Index: 285919 (Open Web Text)

Max Activating Token Index: 673

Text #10

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6417. Min Act: -0.1696

Data Index: 7471784 (Open Web Text)

Max Activating Token Index: 786

Text #11

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6394. Min Act: -0.1691

Data Index: 5718941 (Open Web Text)

Max Activating Token Index: 877

Text #12

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6365. Min Act: -0.1700

Data Index: 1901998 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6454. Min Act: -0.1700

Data Index: 5358098 (Open Web Text)

Max Activating Token Index: 598

Text #14

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6283. Min Act: -0.1692

Data Index: 1500127 (Open Web Text)

Max Activating Token Index: 847

Text #15

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6208. Min Act: -0.1700

Data Index: 749183 (Open Web Text)

Max Activating Token Index: 565

Text #16

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6200. Min Act: -0.1700

Data Index: 4587655 (Open Web Text)

Max Activating Token Index: 253

Text #17

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6232. Min Act: -0.1700

Data Index: 1780663 (Open Web Text)

Max Activating Token Index: 703

Text #18

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6179. Min Act: -0.1700

Data Index: 240670 (Open Web Text)

Max Activating Token Index: 166

Text #19

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6231. Min Act: -0.1700

Data Index: 824411 (Open Web Text)

Max Activating Token Index: 802