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

Dataset: Open Web Text

Neuron 651 in Layer 1

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: 1.7498. Min Range: -1.7498

Max Act: 1.7498. Min Act: -0.1700

Data Index: 394140 (Open Web Text)

Max Activating Token Index: 548

Text #1

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.7187. Min Act: -0.1700

Data Index: 7921049 (Open Web Text)

Max Activating Token Index: 198

Text #2

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.7124. Min Act: -0.1683

Data Index: 7581285 (Open Web Text)

Max Activating Token Index: 845

Text #3

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.7039. Min Act: -0.1700

Data Index: 7401974 (Open Web Text)

Max Activating Token Index: 229

Text #4

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.7033. Min Act: -0.1700

Data Index: 7688831 (Open Web Text)

Max Activating Token Index: 527

Text #5

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6956. Min Act: -0.1700

Data Index: 2194286 (Open Web Text)

Max Activating Token Index: 443

Text #6

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6951. Min Act: -0.1700

Data Index: 8321264 (Open Web Text)

Max Activating Token Index: 543

Text #7

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6844. Min Act: -0.1690

Data Index: 7980196 (Open Web Text)

Max Activating Token Index: 460

Text #8

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6835. Min Act: -0.1700

Data Index: 8286993 (Open Web Text)

Max Activating Token Index: 817

Text #9

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6901. Min Act: -0.1700

Data Index: 2636842 (Open Web Text)

Max Activating Token Index: 49

Text #10

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6779. Min Act: -0.1700

Data Index: 1093874 (Open Web Text)

Max Activating Token Index: 233

Text #11

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6742. Min Act: -0.1700

Data Index: 2342011 (Open Web Text)

Max Activating Token Index: 269

Text #12

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6776. Min Act: -0.1699

Data Index: 3537199 (Open Web Text)

Max Activating Token Index: 67

Text #13

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6764. Min Act: -0.1700

Data Index: 2366161 (Open Web Text)

Max Activating Token Index: 403

Text #14

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6769. Min Act: -0.1700

Data Index: 4629828 (Open Web Text)

Max Activating Token Index: 500

Text #15

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6708. Min Act: -0.1700

Data Index: 7936689 (Open Web Text)

Max Activating Token Index: 159

Text #16

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6713. Min Act: -0.1700

Data Index: 7936690 (Open Web Text)

Max Activating Token Index: 295

Text #17

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6754. Min Act: -0.1700

Data Index: 880729 (Open Web Text)

Max Activating Token Index: 527

Text #18

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6623. Min Act: -0.1700

Data Index: 4759082 (Open Web Text)

Max Activating Token Index: 160

Text #19

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6608. Min Act: -0.1700

Data Index: 7783660 (Open Web Text)

Max Activating Token Index: 719