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

Dataset: Open Web Text

Neuron 1815 in Layer 6

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: 4.1769. Min Range: -4.1769

Max Act: 4.1769. Min Act: -0.1700

Data Index: 1824661 (Open Web Text)

Max Activating Token Index: 258

Text #1

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.1559. Min Act: -0.1700

Data Index: 6048303 (Open Web Text)

Max Activating Token Index: 512

Text #2

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.1454. Min Act: -0.1700

Data Index: 2335950 (Open Web Text)

Max Activating Token Index: 478

Text #3

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.1535. Min Act: -0.1700

Data Index: 7995307 (Open Web Text)

Max Activating Token Index: 187

Text #4

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.1349. Min Act: -0.1700

Data Index: 2265774 (Open Web Text)

Max Activating Token Index: 577

Text #5

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0932. Min Act: -0.1700

Data Index: 5571034 (Open Web Text)

Max Activating Token Index: 908

Text #6

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0653. Min Act: -0.1700

Data Index: 7271401 (Open Web Text)

Max Activating Token Index: 129

Text #7

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0682. Min Act: -0.1700

Data Index: 216593 (Open Web Text)

Max Activating Token Index: 163

Text #8

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0515. Min Act: -0.1700

Data Index: 3583167 (Open Web Text)

Max Activating Token Index: 511

Text #9

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0470. Min Act: -0.1700

Data Index: 7076627 (Open Web Text)

Max Activating Token Index: 851

Text #10

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0243. Min Act: -0.1700

Data Index: 7640160 (Open Web Text)

Max Activating Token Index: 66

Text #11

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0480. Min Act: -0.1700

Data Index: 5434577 (Open Web Text)

Max Activating Token Index: 482

Text #12

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0327. Min Act: -0.1700

Data Index: 6072064 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0089. Min Act: -0.1700

Data Index: 1438188 (Open Web Text)

Max Activating Token Index: 343

Text #14

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0107. Min Act: -0.1700

Data Index: 7271394 (Open Web Text)

Max Activating Token Index: 575

Text #15

Max Range: 4.1769. Min Range: -4.1769

Max Act: 3.9900. Min Act: -0.1700

Data Index: 6508143 (Open Web Text)

Max Activating Token Index: 426

Text #16

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0132. Min Act: -0.1700

Data Index: 3740682 (Open Web Text)

Max Activating Token Index: 996

Text #17

Max Range: 4.1769. Min Range: -4.1769

Max Act: 3.9917. Min Act: -0.1700

Data Index: 1218828 (Open Web Text)

Max Activating Token Index: 544

Text #18

Max Range: 4.1769. Min Range: -4.1769

Max Act: 3.9900. Min Act: -0.1700

Data Index: 2894753 (Open Web Text)

Max Activating Token Index: 74

Text #19

Max Range: 4.1769. Min Range: -4.1769

Max Act: 3.9997. Min Act: -0.1700

Data Index: 7271403 (Open Web Text)

Max Activating Token Index: 688