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

Dataset: Open Web Text

Neuron 2429 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: 4.5193. Min Range: -4.5193

Max Act: 4.5193. Min Act: -0.1700

Data Index: 856752 (Open Web Text)

Max Activating Token Index: 577

Text #1

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.3781. Min Act: -0.1700

Data Index: 1234785 (Open Web Text)

Max Activating Token Index: 426

Text #2

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.4037. Min Act: -0.1700

Data Index: 8676299 (Open Web Text)

Max Activating Token Index: 639

Text #3

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.3843. Min Act: -0.1700

Data Index: 8025004 (Open Web Text)

Max Activating Token Index: 975

Text #4

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.3717. Min Act: -0.1700

Data Index: 5547807 (Open Web Text)

Max Activating Token Index: 659

Text #5

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.3515. Min Act: -0.1700

Data Index: 5492140 (Open Web Text)

Max Activating Token Index: 599

Text #6

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.3584. Min Act: -0.1700

Data Index: 2234611 (Open Web Text)

Max Activating Token Index: 669

Text #7

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.3364. Min Act: -0.1700

Data Index: 3192816 (Open Web Text)

Max Activating Token Index: 454

Text #8

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.3215. Min Act: -0.1700

Data Index: 629538 (Open Web Text)

Max Activating Token Index: 476

Text #9

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.3156. Min Act: -0.1700

Data Index: 1326575 (Open Web Text)

Max Activating Token Index: 788

Text #10

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.2987. Min Act: -0.1700

Data Index: 5031559 (Open Web Text)

Max Activating Token Index: 795

Text #11

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.2964. Min Act: -0.1700

Data Index: 8286116 (Open Web Text)

Max Activating Token Index: 715

Text #12

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.2986. Min Act: -0.1700

Data Index: 7322905 (Open Web Text)

Max Activating Token Index: 608

Text #13

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.2719. Min Act: -0.1700

Data Index: 2593401 (Open Web Text)

Max Activating Token Index: 951

Text #14

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.3084. Min Act: -0.1700

Data Index: 358755 (Open Web Text)

Max Activating Token Index: 70

Text #15

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.2979. Min Act: -0.1700

Data Index: 3341536 (Open Web Text)

Max Activating Token Index: 820

Text #16

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.3003. Min Act: -0.1700

Data Index: 1861235 (Open Web Text)

Max Activating Token Index: 844

Text #17

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.2822. Min Act: -0.1700

Data Index: 6788551 (Open Web Text)

Max Activating Token Index: 851

Text #18

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.2509. Min Act: -0.1700

Data Index: 4046182 (Open Web Text)

Max Activating Token Index: 636

Text #19

Max Range: 4.5193. Min Range: -4.5193

Max Act: 4.2632. Min Act: -0.1700

Data Index: 2402449 (Open Web Text)

Max Activating Token Index: 494