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

Dataset: Open Web Text

Neuron 1450 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: 2.0653. Min Range: -2.0653

Max Act: 2.0653. Min Act: -0.1692

Data Index: 2671726 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9668. Min Act: -0.1700

Data Index: 310304 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9782. Min Act: -0.1700

Data Index: 2363686 (Open Web Text)

Max Activating Token Index: 405

Text #3

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9499. Min Act: -0.1687

Data Index: 3148606 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9252. Min Act: -0.1700

Data Index: 8075173 (Open Web Text)

Max Activating Token Index: 237

Text #5

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9244. Min Act: -0.1698

Data Index: 7061529 (Open Web Text)

Max Activating Token Index: 223

Text #6

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9269. Min Act: -0.1700

Data Index: 6966699 (Open Web Text)

Max Activating Token Index: 301

Text #7

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9391. Min Act: -0.1696

Data Index: 976592 (Open Web Text)

Max Activating Token Index: 597

Text #8

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9380. Min Act: -0.1700

Data Index: 6708986 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9275. Min Act: -0.1684

Data Index: 5612248 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9235. Min Act: -0.1675

Data Index: 6483356 (Open Web Text)

Max Activating Token Index: 472

Text #11

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9226. Min Act: -0.1700

Data Index: 3209389 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9127. Min Act: -0.1700

Data Index: 2597904 (Open Web Text)

Max Activating Token Index: 500

Text #13

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9227. Min Act: -0.1669

Data Index: 65426 (Open Web Text)

Max Activating Token Index: 885

Text #14

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9162. Min Act: -0.1700

Data Index: 1266899 (Open Web Text)

Max Activating Token Index: 656

Text #15

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9123. Min Act: -0.1697

Data Index: 5545015 (Open Web Text)

Max Activating Token Index: 282

Text #16

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9237. Min Act: -0.1696

Data Index: 4470020 (Open Web Text)

Max Activating Token Index: 460

Text #17

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9117. Min Act: -0.1700

Data Index: 4173954 (Open Web Text)

Max Activating Token Index: 498

Text #18

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9099. Min Act: -0.1694

Data Index: 3962290 (Open Web Text)

Max Activating Token Index: 63

Text #19

Max Range: 2.0653. Min Range: -2.0653

Max Act: 1.9121. Min Act: -0.1692

Data Index: 3786746 (Open Web Text)

Max Activating Token Index: 741