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

Dataset: Open Web Text

Neuron 2131 in Layer 5

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: 3.0575. Min Range: -3.0575

Max Act: 3.0374. Min Act: -0.1700

Data Index: 1595948 (Open Web Text)

Max Activating Token Index: 956

Text #1

Max Range: 3.0575. Min Range: -3.0575

Max Act: 3.0450. Min Act: -0.1700

Data Index: 7661741 (Open Web Text)

Max Activating Token Index: 775

Text #2

Max Range: 3.0575. Min Range: -3.0575

Max Act: 3.0403. Min Act: -0.1700

Data Index: 885103 (Open Web Text)

Max Activating Token Index: 497

Text #3

Max Range: 3.0575. Min Range: -3.0575

Max Act: 3.0455. Min Act: -0.1700

Data Index: 8127609 (Open Web Text)

Max Activating Token Index: 555

Text #4

Max Range: 3.0575. Min Range: -3.0575

Max Act: 3.0282. Min Act: -0.1700

Data Index: 3668966 (Open Web Text)

Max Activating Token Index: 288

Text #5

Max Range: 3.0575. Min Range: -3.0575

Max Act: 3.0011. Min Act: -0.1700

Data Index: 7123537 (Open Web Text)

Max Activating Token Index: 712

Text #6

Max Range: 3.0575. Min Range: -3.0575

Max Act: 3.0575. Min Act: -0.1700

Data Index: 7192887 (Open Web Text)

Max Activating Token Index: 998

Text #7

Max Range: 3.0575. Min Range: -3.0575

Max Act: 3.0137. Min Act: -0.1700

Data Index: 6850938 (Open Web Text)

Max Activating Token Index: 548

Text #8

Max Range: 3.0575. Min Range: -3.0575

Max Act: 3.0298. Min Act: -0.1700

Data Index: 1833081 (Open Web Text)

Max Activating Token Index: 236

Text #9

Max Range: 3.0575. Min Range: -3.0575

Max Act: 3.0079. Min Act: -0.1700

Data Index: 2403329 (Open Web Text)

Max Activating Token Index: 178

Text #10

Max Range: 3.0575. Min Range: -3.0575

Max Act: 3.0026. Min Act: -0.1700

Data Index: 4751150 (Open Web Text)

Max Activating Token Index: 94

Text #11

Max Range: 3.0575. Min Range: -3.0575

Max Act: 3.0270. Min Act: -0.1700

Data Index: 1299832 (Open Web Text)

Max Activating Token Index: 793

Text #12

Max Range: 3.0575. Min Range: -3.0575

Max Act: 2.9721. Min Act: -0.1700

Data Index: 7521108 (Open Web Text)

Max Activating Token Index: 345

Text #13

Max Range: 3.0575. Min Range: -3.0575

Max Act: 2.9620. Min Act: -0.1700

Data Index: 3686797 (Open Web Text)

Max Activating Token Index: 503

Text #14

Max Range: 3.0575. Min Range: -3.0575

Max Act: 2.9927. Min Act: -0.1700

Data Index: 4714467 (Open Web Text)

Max Activating Token Index: 905

Text #15

Max Range: 3.0575. Min Range: -3.0575

Max Act: 3.0014. Min Act: -0.1700

Data Index: 2597002 (Open Web Text)

Max Activating Token Index: 782

Text #16

Max Range: 3.0575. Min Range: -3.0575

Max Act: 2.9726. Min Act: -0.1700

Data Index: 25847 (Open Web Text)

Max Activating Token Index: 1015

Text #17

Max Range: 3.0575. Min Range: -3.0575

Max Act: 2.9995. Min Act: -0.1700

Data Index: 3384778 (Open Web Text)

Max Activating Token Index: 214

Text #18

Max Range: 3.0575. Min Range: -3.0575

Max Act: 2.9702. Min Act: -0.1700

Data Index: 2508849 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 3.0575. Min Range: -3.0575

Max Act: 2.9709. Min Act: -0.1700

Data Index: 1604921 (Open Web Text)

Max Activating Token Index: 342