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

Dataset: Open Web Text

Neuron 519 in Layer 0

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: 3.8685. Min Range: -3.8685

Max Act: 3.8685. Min Act: -0.1700

Data Index: 7286270 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.8613. Min Act: -0.1700

Data Index: 2552015 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.8053. Min Act: -0.1700

Data Index: 482432 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.8063. Min Act: -0.1700

Data Index: 1811965 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.8279. Min Act: -0.1700

Data Index: 5578627 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.8128. Min Act: -0.1700

Data Index: 616206 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.8182. Min Act: -0.1700

Data Index: 7010744 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.7693. Min Act: -0.1700

Data Index: 3671765 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.7779. Min Act: -0.1700

Data Index: 2444935 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.7943. Min Act: -0.1700

Data Index: 7241378 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.7846. Min Act: -0.1700

Data Index: 1812728 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.7432. Min Act: -0.1700

Data Index: 7456025 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.7434. Min Act: -0.1700

Data Index: 3089986 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.7568. Min Act: -0.1700

Data Index: 6535519 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.7621. Min Act: -0.1700

Data Index: 873725 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.7395. Min Act: -0.1700

Data Index: 556770 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.7471. Min Act: -0.1700

Data Index: 5551007 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.7401. Min Act: -0.1700

Data Index: 4912677 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.7548. Min Act: -0.1700

Data Index: 4413715 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.8685. Min Range: -3.8685

Max Act: 3.7416. Min Act: -0.1700

Data Index: 3558488 (Open Web Text)

Max Activating Token Index: 9