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

Dataset: Open Web Text

Neuron 36 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: 4.9329. Min Range: -4.9329

Max Act: 4.9151. Min Act: -0.1700

Data Index: 787350 (Open Web Text)

Max Activating Token Index: 299

Text #1

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.9329. Min Act: -0.1700

Data Index: 1730114 (Open Web Text)

Max Activating Token Index: 270

Text #2

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.8239. Min Act: -0.1700

Data Index: 1579350 (Open Web Text)

Max Activating Token Index: 493

Text #3

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.7711. Min Act: -0.1700

Data Index: 4487073 (Open Web Text)

Max Activating Token Index: 832

Text #4

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.7657. Min Act: -0.1700

Data Index: 8460468 (Open Web Text)

Max Activating Token Index: 216

Text #5

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.7918. Min Act: -0.1700

Data Index: 6699563 (Open Web Text)

Max Activating Token Index: 135

Text #6

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.7720. Min Act: -0.1700

Data Index: 1525316 (Open Web Text)

Max Activating Token Index: 787

Text #7

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.7310. Min Act: -0.1700

Data Index: 7239894 (Open Web Text)

Max Activating Token Index: 213

Text #8

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.7273. Min Act: -0.1700

Data Index: 6018396 (Open Web Text)

Max Activating Token Index: 427

Text #9

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.7041. Min Act: -0.1700

Data Index: 3449823 (Open Web Text)

Max Activating Token Index: 229

Text #10

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.6982. Min Act: -0.1700

Data Index: 5603718 (Open Web Text)

Max Activating Token Index: 681

Text #11

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.7080. Min Act: -0.1700

Data Index: 5012333 (Open Web Text)

Max Activating Token Index: 567

Text #12

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.6985. Min Act: -0.1700

Data Index: 902198 (Open Web Text)

Max Activating Token Index: 1005

Text #13

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.6691. Min Act: -0.1700

Data Index: 3556746 (Open Web Text)

Max Activating Token Index: 615

Text #14

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.6449. Min Act: -0.1700

Data Index: 675207 (Open Web Text)

Max Activating Token Index: 752

Text #15

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.6657. Min Act: -0.1700

Data Index: 1557583 (Open Web Text)

Max Activating Token Index: 628

Text #16

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.6612. Min Act: -0.1700

Data Index: 1229814 (Open Web Text)

Max Activating Token Index: 88

Text #17

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.6240. Min Act: -0.1700

Data Index: 6317390 (Open Web Text)

Max Activating Token Index: 454

Text #18

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.6317. Min Act: -0.1700

Data Index: 3591509 (Open Web Text)

Max Activating Token Index: 323

Text #19

Max Range: 4.9329. Min Range: -4.9329

Max Act: 4.6870. Min Act: -0.1700

Data Index: 1514844 (Open Web Text)

Max Activating Token Index: 216