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

Dataset: Open Web Text

Neuron 306 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: 1.6485. Min Range: -1.6485

Max Act: 1.6485. Min Act: -0.1699

Data Index: 3689163 (Open Web Text)

Max Activating Token Index: 637

Text #1

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6478. Min Act: -0.1700

Data Index: 6874879 (Open Web Text)

Max Activating Token Index: 23

Text #2

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6367. Min Act: -0.1700

Data Index: 6599138 (Open Web Text)

Max Activating Token Index: 129

Text #3

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6326. Min Act: -0.1700

Data Index: 7025299 (Open Web Text)

Max Activating Token Index: 393

Text #4

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6324. Min Act: -0.1697

Data Index: 5189997 (Open Web Text)

Max Activating Token Index: 678

Text #5

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6260. Min Act: -0.1700

Data Index: 8617575 (Open Web Text)

Max Activating Token Index: 620

Text #6

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6276. Min Act: -0.1700

Data Index: 7277139 (Open Web Text)

Max Activating Token Index: 610

Text #7

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6362. Min Act: -0.1700

Data Index: 3280428 (Open Web Text)

Max Activating Token Index: 178

Text #8

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6257. Min Act: -0.1700

Data Index: 3602356 (Open Web Text)

Max Activating Token Index: 949

Text #9

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6184. Min Act: -0.1700

Data Index: 8443708 (Open Web Text)

Max Activating Token Index: 24

Text #10

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6227. Min Act: -0.1700

Data Index: 2088698 (Open Web Text)

Max Activating Token Index: 754

Text #11

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6152. Min Act: -0.1700

Data Index: 7328266 (Open Web Text)

Max Activating Token Index: 402

Text #12

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6062. Min Act: -0.1700

Data Index: 73539 (Open Web Text)

Max Activating Token Index: 550

Text #13

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6074. Min Act: -0.1700

Data Index: 4638683 (Open Web Text)

Max Activating Token Index: 728

Text #14

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6156. Min Act: -0.1698

Data Index: 2146088 (Open Web Text)

Max Activating Token Index: 252

Text #15

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6093. Min Act: -0.1700

Data Index: 609431 (Open Web Text)

Max Activating Token Index: 521

Text #16

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6078. Min Act: -0.1700

Data Index: 902038 (Open Web Text)

Max Activating Token Index: 996

Text #17

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6070. Min Act: -0.1700

Data Index: 3472835 (Open Web Text)

Max Activating Token Index: 576

Text #18

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6044. Min Act: -0.1699

Data Index: 4596809 (Open Web Text)

Max Activating Token Index: 821

Text #19

Max Range: 1.6485. Min Range: -1.6485

Max Act: 1.6008. Min Act: -0.1700

Data Index: 4732958 (Open Web Text)

Max Activating Token Index: 1016