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

Dataset: Open Web Text

Neuron 2456 in Layer 4

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: 3.4555. Min Range: -3.4555

Max Act: 3.4555. Min Act: -0.1700

Data Index: 5354517 (Open Web Text)

Max Activating Token Index: 768

Text #1

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.4454. Min Act: -0.1700

Data Index: 1406441 (Open Web Text)

Max Activating Token Index: 641

Text #2

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.4119. Min Act: -0.1700

Data Index: 3956384 (Open Web Text)

Max Activating Token Index: 582

Text #3

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.3585. Min Act: -0.1700

Data Index: 4895047 (Open Web Text)

Max Activating Token Index: 581

Text #4

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.3731. Min Act: -0.1700

Data Index: 4415899 (Open Web Text)

Max Activating Token Index: 551

Text #5

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.3538. Min Act: -0.1700

Data Index: 6494549 (Open Web Text)

Max Activating Token Index: 51

Text #6

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.3449. Min Act: -0.1700

Data Index: 7633275 (Open Web Text)

Max Activating Token Index: 27

Text #7

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.3471. Min Act: -0.1700

Data Index: 1018073 (Open Web Text)

Max Activating Token Index: 235

Text #8

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.3256. Min Act: -0.1700

Data Index: 3956710 (Open Web Text)

Max Activating Token Index: 154

Text #9

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.3252. Min Act: -0.1700

Data Index: 4809487 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.2920. Min Act: -0.1700

Data Index: 7971091 (Open Web Text)

Max Activating Token Index: 720

Text #11

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.3287. Min Act: -0.1700

Data Index: 2199938 (Open Web Text)

Max Activating Token Index: 240

Text #12

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.3039. Min Act: -0.1700

Data Index: 5120036 (Open Web Text)

Max Activating Token Index: 82

Text #13

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.2993. Min Act: -0.1700

Data Index: 3901520 (Open Web Text)

Max Activating Token Index: 43

Text #14

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.2718. Min Act: -0.1700

Data Index: 2758946 (Open Web Text)

Max Activating Token Index: 950

Text #15

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.2803. Min Act: -0.1700

Data Index: 8149667 (Open Web Text)

Max Activating Token Index: 407

Text #16

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.2709. Min Act: -0.1700

Data Index: 4941545 (Open Web Text)

Max Activating Token Index: 690

Text #17

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.2700. Min Act: -0.1700

Data Index: 1516050 (Open Web Text)

Max Activating Token Index: 531

Text #18

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.2928. Min Act: -0.1700

Data Index: 5410989 (Open Web Text)

Max Activating Token Index: 454

Text #19

Max Range: 3.4555. Min Range: -3.4555

Max Act: 3.2684. Min Act: -0.1700

Data Index: 6617264 (Open Web Text)

Max Activating Token Index: 262